Opening the Ottoman Archive

You want to do granular research on the Ottoman Empire and its successor states, but don't read Ottoman Turkish. Do you throw up you hands or look for a new set of powerful tools?

This article | The Ottoman Archive use case | The challenge | Let’s look at some documents | How can we read these documents? | Testing and validation of model outputs | Accessing and understanding archives | In conclusion | Appendix One: GitHub repository | Appendix Two: Project documentation

This article

This article builds on my December 4th 2025 Substack article ‘A New Lens into the Archives’, and on my subsequent December 20th 2025 article in which I looked at mid-C20th Yiddish as a demanding edge case for LLM-enabled Handwritten Text Recognition. In those two December articles I examined the impact Google’s Gemini 3 Pro visually grounded large language model will have on machine transcription and on historians’ abilities to interrogate archives. It was a Eureka moment for me, who has been involved with history tech since 2012, and with machine transcription since 2018.¹ ²

In my new article, I propose a novel approach to historical research in which LLM-based machine transcription is integrated by general historians into their working methods to increase the scope, scale and impact of their work, using the field of Ottoman studies and languages as the use case. My proposal is significantly broader than applying machine transcription to research. It is an argument that historians can integrate LLMs into their existing work flows, and can improve on those workflows, to produce sophistiated, granular, auditable results which meet good historical and archival practice. The article draws on my thinking about ‘New Skills for Historians’ which I first described in July 2024 at an internal National Archives workshop and in November 2024 at an IHR Digital History seminar.³ ⁴

I present this as a work in progress. To stimulate your thinking, your engagement, your push back, and your improvements. My interest, as always, since I started work as a public historian in 2012, is to create useful tools and to encourage collaboration, and this is no different.

The proof of the pudding will be the production and publication of historical research using such techniques. The article concludes with a call to like-minded historians to engage with me and fellow members of the ai + history collaboratory I convene to structure and conduct a small Proof of Concept for publication using the tools and methods I describe in this article. I propose we identify and work collaboratively on a cross-cultural and cross-linguistic topic of importance in the Ottoman Archive. In working together all participants would have a chance to learn, validate and of course improve these tools and methods and to explore their relevance to their own research.

The Ottoman Archive use case

Starting with Ottoman Turkish, a demanding Right-To-Left language, I show how Ottoman Turkish and other languages of the Ottoman Empire, such as Albanian, Bulgarian, Greek, and Armenian can be made accessible and readable to generalist historians. Four of these five languages have non-Roman alphabets and are challenging for researchers brought up on English, French, German and Spanish.

I position command of language as necessary, but not sufficient, for historians to access Ottoman archival material. The general historian additionally needs the ability to find relevant archives, to identify which archives have digitised material, to discover and navigate the structure of physical and digitised archives at fonds level, to understand existing metadata (in whatever language it is presented), and to access page level images of printed and handwritten documents. I show how I have achieved this in my own experiments, especially with archives of digital Ottoman Turkish material, but my methods are generalisable to archives containing Albanian, Bulgarian, Greek, and Armenian materials, as well as for modern Turkish.

My approach opens the conceptual Ottoman Archive, as well as physical and digital archives. Small neglected water damaged archives outside capital cities, as well as heavily digitised archives, which use IIIF to make available text and cartography. Archives such as ISAM in Istanbul, the National Library of Greece in Athens, and the Endangered Archives Scheme run by the British Library.⁵ ⁶ ⁷ Archives in successor states of the Ottoman Empire, as well as the national and regional archives of former ‘Great European Powers’ who intervened in the Ottoman Empire.

‘Balkan States’, map from “Stanford’s Compendium of Geography and Travel: Europe” Volume 1, 1899 ⁸

The challenge

The redrawing of the borders of the Ottoman Empire in the C19th and early C20th, had dramatic consequences politically and militarily for the whole of Europe, Asia Minor, the Caucasus, and the Near and Middle East. It involved and raised issues relating to perceived and claimed ethnic identity, in which language was a key signifier of identity.

‘Carte Ethnografique de la Macédoine: Point de vue serbe’, Map from “Report of the International Commission To Inquire into the Causes and Conduct of the Balkan Wars” 1914; ‘Carte Ethnografique de la Macédoine: Point de vue bulgare’, Map from “Report of the International Commission To Inquire into the Causes and Conduct of the Balkan Wars” 1914 ⁹

One of the most dramatic changes came in the 1920s with the end of Ottoman Turkish as a bureaucratic writing system, with its complex Right-To-Left perso-arabic script, and its replacement by Modern Turkish, written with a romanicised alphabet and a reformed phonetic and grammatical system. This dramatic shift took place at the same time as the creation of a Turkish state, centred on Anatolia.

But changes from early in the C19th also impacted the orthography and broader writing systems of many other languages spoken and written in the Ottoman Empire. As Greeks, Bulgars, Albanians and many other groups of intermingled peoples sought to define themselves, and assert their cultural and political identity, they looked to language and writing system reforms.

‘The Albanian Alphabet,’ Drita, 1907, Issue 90, p.4, bottom of RH column ¹⁰

This makes for a challenging fluid evidentiary environment in which to conduct historical research, and has meant that research into events and issues of broad import have often been restricted to specialist research groups and linguistically focused historians.

Let’s look at some documents

So how big is the challenge for a historian? Let me show you five languages and five different writing systems, and you will begin to visualise (literally visualise) the size of the task.

Ottoman Turkish

Takvîm-i Vekâyi [Ottoman Government Gazette], Issue 185, 1839. Masthead and RH and LH columns of first page of four page document¹¹

Şanizade History by Şanizade Mehmed Ataullah Efendi, 1242/1826 [CE], publication date 1284/1868 [CE]. ISAM.¹²

Sadâret Correspondence (Outgoing to Inspector-General), İSAM Kütüphanesi Arşivi (İKA). Semder: Bâb-ı Âlî / Dâ’ire-i Ṣadâret-i ‘Uẓmâ / Mektûbî Ḳalemi; Recipient: Rûm-ili Vilâyât-ı Şâhâne Müfettişliği (Hüseyin Hilmi Paşa); Date: 22 Kânûn-ı Evvel 1319 [Rumi], 4 January 1904 [Gregorian]; p.1 of 2 ¹³

Bulgarian

БАЛКАНЪ [БАЛКАН; Balkan], Year I — Ruse, 10 June 1898 [O.S.] — Issue 7, St. Cyril and Methodius National Library of Bulgaria, republished by the British Library Endangered Archives project, EAP 698/1/8 ¹⁴

Handwritten pre-orthographic reform Bulgarian cyrillic. July 3, 1905. ISAM: IKA HHP-H-2-b-dos.1-1396 ¹⁵

Greek

ΕΠΤΑΛΟΦΟΣ ΝΕΑ - “Heptalophos Nea” (Seven-Hilled News), Issue 20, October 31st 1865, p.1 ¹⁶

Albanian

Drita [The Light], January 1st 1908, Issue 95. p.1 (of 4). Published Sofia, Bulgaria. Albanian romanised script; Ottoman script ¹⁷

Armenian

‘Birth certificate Author’s Paternal Grandmother, Arusiak Adamyants born on April 24, 1904 in Shushi. The text is bilingual with Russian on the left. This is an good example of developed writing culture present in Artsakh at the turn of the 20th century as it is executed by an anonymous clerk in the Municipality of Shushi (then part of the Russian Empire). ¹⁸

How can we read these documents?

I have developed a system to read the five written languages above, using the concept of HTR skills markup files, which I first proposed in December 2025.¹⁹ This development process has been both conceptual and empirical, and has been conducted iteratively in collaboration with Claude Opus 4.5 as my primary tool for work process and skill file development. It is still at the Proof of Concept stage and is not yet mature and scalable.

For each language I have conducted an a priori review of the linguistic challenges of that language, and have structured a work process tailored to that language. In the case of three languages (Ottoman Turkish, Bulgarian, and Greek), which each have demanding non-Roman character based alphabets and phonetic systems, I elected to go with a two-stage architecture. The first stage being visual capture of the script as a digital transcription. The second stage being a semantically driven transliteration, translation, named entity extraction, and contextualised summarisation of the digital transcription. In the case of Albanian and modern Turkish I went with a single-stage architecture which combined visual capture and semantically driven transliteration, translation, named entity extraction, and contextualised summarisation of the digital transcription. I am still debating the best approach to Armenian. I have had success with a one-stage approach for Armenian, as reported in my December 4th 2025 Generative Lives article (“A New Lens into the Archive”), but I may move over to a two-stage approach for maximum flexibiliy with both printed and handwritten documents.

I elected to use Gemini 3 Pro Preview for the Stage One visual capture, operating at unusual settings designed to maximise visual capture and to avoid or minimise any semantic intervention (temperature = 0.2; media resolution = high; thinking = low; top P = 0.0.15). For the Stage Two semantic processing I elected to use Claude Opus 4.5, operating at standard settings (temperature = 1.0; thinking = high; top P = 0.95). For one-stage processing I have tried both Gemini and Claude, but prefer Claude because of the advantages of a standardised project platform based on Claude HTR projects.

Methodology

Reading printed documents

Let me show you some of the outputs of my work for a range of genres - historical gazettes, newspapers, and maps - all from printed sources. I have tested all the above genres for Ottoman Turkish, and have tested limited genres for other languages - Albanian (newspapers), Bulgarian (newspapers), Greek (government gazette; newspapers), and Armenian (birth certificate).

The quality of output is not identical. Reuse of the same HTR skills files (both visual capture and semantic processing of the visual capture to produce transliteration, translation, named entity extraction and contextualised summarisation) on the same underlying image does show small variances in output once a skills file has been iterated and optimised for a specific language and genre. But I have measured these variances using a range of measures (see section titled “Testing and validating model outputs”) and have found the variances to rarely affect the consistent extraction of the same named entities from repeated model outputs for the same image. In other words, an historian wishing to explore a range of documents looking for a particular category of named entity and a specific instance of that entity is likely to find it consistently in model outputs.

I still need to prove this at scale, but my experiments look very positive. Ultimately, individual historians will need to form their own views on whether the output of HTR skills models is sufficiently stable for their own granular research.

Reading printed historical gazettes

Ἑφημερίς τῆς Κυβερνήσεως, Greek Government Gazette, 14 Ἰανουαρίου 1833 [Julian], 26 January 1833 [Gregrorian], Issue 1. In the facsmilie of the gazette image, LH column is Greek; RH colum is German. Original script and modernised English translation.²⁰

Extract from V3-T-Greek skills markdown file, created and stored in Claude Greek HTR project ²¹

Extract from the Claude Opus 4.5 model output, processing Gemini 3 Pro Preview visual capture of Greek script, stored in Claude Greek HTR project ²²

Reading newspapers

Peyam newspaper. p.1 of the 14 Ağustos 1335 (Rumi)/August 14, 1919 (Gregorian) issue ²³

Extract from V3-T-Newspaper Protocol designed for Second Constitution period Ottoman Turkish newspaper specifying structured JSON model output

Extract from model output using V3-T-Newspaper Protocol HTR skills file applied to Gemini visual capture of the perso-arabic script by Claude Ous 4.5 in Ottoman Turkish HTR project

Reading maps

Ottoman General Staff map. Ottoman Turkish script. Multiple cartouches. ca. 1890. ²⁴

Ottoman General Staff map. Ottoman Turkish script. Data table. ca. 1890. ²⁵

Text extraction from Ottoman General Staff map using a one-stage approach by Claude Opus 4.5 in the Ottoman Turkish HTR project as a proof of concept of reading Ottoman Turkish script in Ottoman maps

Reading handwritten bureaucratic and personal documents

Handwriting introduces greater variance in character and word formation, with writer specific usage of ligatures, up and down strokes, diacritics and other palaeographical features, together with greater irregularity in layout, such as slanted handwriting.

I have experimented with some success with LLM-enabled machine transcription of handwritten documents, including bureaucratic and personal hand written documents in Ottoman Turkish and modern Turkish, but will not show those outputs here since it is relatively early days.

Testing and validating model outputs

A key part of designing an HTR skills markdown file is to test and validate the outputs it produces.

I used three different types of validation process:

1. Character error (cer) and word error (wer) calculation. These calculations used python scripts written by a different instances of the LLMs using industry standrad definitions of error rates. I applied these calculations to model outputs at a line by line as well as an article by article and a page by page level. This is only possible where a known validated ground truth or gold standard exists for a specific text.

2. Variance analysis. This examines the variance of model outputs from the same image using the same HTR skills file run multiple times. It does not require known validated ground truth or gold standard.

3. Semantic consistency analysis. This uses Named Entity extraction on model outputs from the same image using the same HTR skills file run multiple times. The test checks that the same Named Entities appeared in all model outputs, even if there was some variance in the transcription and/or the transliteration between model runs. It does not require known validated ground truth or gold standard. In many ways this is the key test for an historian - it is proxy for whether reliable semantic content is being produced using these tools.

Below is an example of Claude Opus 4.5 checking the line by line accuracy of visual capture by Gemini 3 Pro Preview of perso-arabic script from an Ottoman Turkish text. All my experiments are logged and allocated an Experiment Number. This was Experiment 149, conducted on December 28th 2025. The text which had been captured visually as a perso-arabic transcription was the first page of Şanizade History by Şanizade Mehmed Ataullah Efendi, 1242/1826 [CE], publication date 1284/1868 [CE], which is available in the ISAM digital library in Istanbul.

The final validation is of course by specialists who have deep understanding of the various scripts I have been processing. I have shared an example of the Ottoman Turkish official gazette visual capture and semantic processing with a scholar who specialises in this field, who commented on the accuracy of the visual capture of the perso-arabic script and on the high quality of the transliteration and translation, and I am hoping that this article encourages other specialists to approach me to discuss my work. Everything I do is CCBY 4 and I will be delighted to work with any scholar interested in engaging in these nascent methodologies and to explore whether they may be of utility in supporting their own research work.

Accessing and understanding archives

Below are two examples of how I worked with specific language based Claude HTR projects to identify and understand archives and fonds structure.

Seeking to understand a largely Ottoman Turkish fonds structure

Situation

I discovered the wonderful digital collections of İslam Araştırmaları Merkezi / Centre for Islamic Studies in Istanbul and wanted to explore one specific fonds called the “Hüseyin Hilmi Pasha Documents”. The fonds structure was available digitally in English.

The fonds was extensive in size and was described as “a collection of correspondence from Hüseyin Hilmi Pasha, who served as Grand Vizier during the March 31st Incident, [which] constitutes an important resource for researchers interested in late Ottoman history, the Committee of Union and Progress, the Balkans, and Macedonia. Comprising 3328 documents from the period 1714-1928, the collection is classified into 26 folders and 1729 files.”

Navigating the ISAM website in English (modern Turkish is also available) my starting point to understand the Fonds was the “Fund HHP - Hüseyin Hilmi Pasha Documents” webpage.

I had become interested in a sub-fonds concerning the Rumelia Directorate, having discovered by chance an Albanian newspaper containing both Albanian romanised script and what I guessed was Ottoman Turkish or possibly Albanian written in Ottoman Turkish. Subsequently, through linguistic analysis within the Claude Albanian HTR project, I used an Ottoman Turkish HTR skills markdown file and confirmed it was Ottoman Turkish.

Drita [The Light], January 1st 1908, Issue 95, pp.3-4 (whole issue = pp.1-4). Published Sofia, Bulgaria. Albanian romanised script; Ottoman script. Sourced from ISAM (İslam Araştırmaları Merkezi / Centre for Islamic Studies). Fonds: Hüseyin Hilmi Pasha Documents; sub-fonds: Rumelia Inspectorate; series: Foreign activities and the foreign press in the Balkans; sub-series: Foreign Press; file: Macedonia issue; item number: 0621 [Drita_1907_1808_hhp_0621.pdf]

I decided to create a project file, which would contain the sub-fonds structure relating to the Rumelia Directorate, which I could then interrogate to help me find more documents of interest in Ottoman Turkish, but potentially in other languages such as Albanian, Bulgarian and Greek.

Working with Claude

Through conversation with Claude, I discovered that ISAM uses AtoM 2.8.2 (Access to Memory), an open-source archival management system that supports EAD (Encoded Archival Description) exports. This was significant: rather than manually navigating hundreds of catalogue entries through the web interface, I could potentially extract structured XML data at the series level. Claude helped me construct the correct URL pattern for EAD exports and we successfully retrieved the full XML for two series within the Rumelia Inspectorate sub-fonds: HHP-H-1 (Activities/Faaliyetleri) with 104 items and HHP-H-2 (Foreign Activities and Foreign Press in the Balkans) with 135 items. Claude then parsed this XML, extracting item-level metadata including unit identifiers, titles, physical descriptions, languages, dates, and—crucially—the granular Ottoman archival document types embedded in scope and content notes (tahrirat, tercüme, telgraf, layiha, and so forth).

The resulting analysis revealed the linguistic complexity of the collection: across 239 items containing 645 documents, Ottoman Turkish dominated (90.8%), but French diplomatic correspondence comprised 9.2%, with smaller quantities of Bulgarian, English, and Arabic. More surprising was the discovery of 162 newspaper clippings from European and Balkan press—Le Figaro, Le Temps, Neue Freie Presse, The New York Herald—preserved because Hüseyin Hilmi Paşa’s intelligence apparatus monitored foreign coverage of the Macedonian Question. Claude generated JSON data files and comparative markdown reports that I could save to my planned Balkan Ottoman HTR GitHub repository, transforming my manual web inspection into a structured dataset I could query and filter.²⁶

One significant finding relating to language emerged from cross-referencing the EAD metadata against visual inspection of the actual documents. The catalogue listed item HHP-H-2-b-dos.1-0621 as “Bulgarian” (language code: bul). But when I examined the PDF—the Drita newspaper that had first drawn me to this collection—I already knew from my Albanian HTR work that this was not Bulgarian at all. It was Albanian, published in Sofia for the Albanian diaspora, with approximately 85-90% of its content in pre-standardisation Latin-script Albanian and 10-15% in Ottoman Arabic script. The cataloguers, seeing a newspaper from Sofia with Cyrillic in the masthead context, had apparently coded it as Bulgarian without recognising the Albanian content. This raised an immediate question: how many other items catalogued as “Bulgarian” might actually be Albanian? I pulled another item flagged as Bulgarian—HHP-H-2-b-dos.1-1396—and examined the handwritten pages. This time, Claude confirmed it genuinely was Bulgarian: handwritten Cyrillic from Sofia dated July 1905, discussing Serbian-Bulgarian relations over Macedonia, with archaic pre-reform orthography (the letters ѣ and ѩ visible throughout). The metadata error was specific to Drita, not systematic—but it demonstrated why visual verification remains essential even when working with professionally catalogued digital archives.

Struggling with metadata and needing a content overview

Situation

I was looking for a mid-C19th Greek newspaper in digital form to complement a Greek government gazette exemplar I had already identified and processed. I had found a digitised page online from what I believed was a Constantinople Greek language newspaper from 1865. But I knew nothing about the archive, couldn’t read the Greek language metadata, and had no sense of the content. I prompted Claude within my Greek HTR project context to learn more so I could triage the document.

My prompt

How did Claude respond and why?

Claude as instructed in the Greek HTR project, with access to my prior conversation history and Greek HTR project files, had strong contextual understanding of my approach to HTR, including my desire for original script, transliteration and translation, together with NER and contextualisation. This means that when asked to assist with the identification of a page of a Greek newspaper and to contextualise it within the context of Greek language metadata provided by a digital archive, it did it in a well structured and helpful manner which was relevant to my goals as an historian. It used its native wits, rather than following a protocol I had written to interrogate metadata. Though of course that is the next step - a set of work processes to interrogate archival metadata, including use of Claude to access and inerrogate archival APIs (an approach I suggested in July 2024 to the TNA).²⁷

This was Claude’s Thought Process, which itself is a source of valuable insight:

The user has uploaded an image of what appears to be a page from a 19th-century Greek newspaper called “ΕΠΤΑΛΟΦΟΣ ΝΕΑ” (Heptalophos Nea / Seven-Hilled News - a reference to Constantinople, the “city of seven hills”). They want me to analyze and contextualize this page.

Let me first examine the image carefully and then apply my Greek HTR skills to analyze it. The user has provided helpful metadata from the Medusa digital repository that confirms this is indeed from Constantinople, 1865.

Looking at the image, I can see:

1. A masthead “ΕΠΤΑΛΟΦΟΣ ΝΕΑ” (with decorative typography)

2. An engraved illustration showing what appears to be a panoramic view of Constantinople

3. The date line appears to read “31 ΟΚΤΩΒΡΙΟΥ” and “ΕΤΟΣ ΠΡΩΤΟΝ” (Year First) with “ΑΡΙΘΜΟΣ 20”

4. Two columns of Greek text

5. Headlines including “ΔΡΑΜΑΤΙΚΑΙ ΜΕΛΕΤΑΙ” and “ΙΣΤΟΡΙΚΟΝ ΕΝΔΙΑΦΕΡΟΝ ΤΩΝ ΚΩΜΩΔΙΩΝ ΤΟΥ ΑΡΙΣΤΟΦΑΝΟΥΣ”

This is fascinating - a Greek literary/cultural newspaper from Ottoman Constantinople in 1865. Let me analyze this properly using the V3-T-Greek methodology to provide context and translation.

The user wants me to “analyse and contextualise” the page. Given their preference for a Socratic approach and their expertise in HTR for historical Greek documents, I should:

1. Examine the image

2. Provide historical context about the newspaper and its setting

3. Analyze the content - the article about Aristophanes’ comedies

4. Connect this to the broader context of Greek intellectual life in Ottoman Constantinople

I’ll zoom in on the details, carefully tracing the typography and examining the intricate layout of this historical document. The panoramic illustration and precise column formatting reveal the newspaper’s sophisticated design for its era.

Here is the model output which builds on the thought processs:

Looking at this fascinating page, I’m immediately struck by several elements that deserve exploration. Before I dive into a full analysis, let me pose some guiding questions that might help us think through what we’re seeing:

What does the newspaper’s name tell us? “ΕΠΤΑΛΟΦΟΣ ΝΕΑ” - “Heptalophos Nea” (Seven-Hilled News) - is a direct reference to Constantinople as the “city of seven hills,” mirroring Rome’s ancient epithet. What might this naming choice suggest about how Greek intellectuals in Constantinople conceived of their city’s identity and continuity with classical civilization?

What’s the significance of the visual program?

The masthead features an engraved panorama of Constantinople - I can make out minarets, the Golden Horn, and the characteristic silhouette of the city. This is quite deliberate editorial choice for a Greek publication under Ottoman rule.

Let me examine the textual content more closely:

The Articles on This Page

I can identify two related articles, both concerning Aristophanes:

Left Column:

ΔΡΑΜΑΤΙΚΑΙ ΜΕΛΕΤΑΙ (Dramatikai Meletai) — “Dramatic Studies”

• (Συνέχεια ἀριθμ. ιθ΄) — Continuation from number 19

• ΥΦΟΣ ΤΟΥ ΑΡΙΣΤΟΦΑΝΟΥΣ — “The Style of Aristophanes”

Right Column (continuing from left):

ΙΣΤΟΡΙΚΟΝ ΕΝΔΙΑΦΕΡΟΝ ΤΩΝ ΚΩΜΩΔΙΩΝ ΤΟΥ ΑΡΙΣΤΟΦΑΝΟΥΣ “Historical Interest of Aristophanes’ Comedies”

---

Historical Contextualization

This raises several fascinating questions worth exploring:

1. Why Aristophanes in Constantinople, 1865?

The Greek communities of Ottoman Constantinople (the “Rum millet”) maintained a vibrant intellectual culture. But why focus on Aristophanes specifically? Consider:

• Aristophanes’ comedies offer direct access to Athenian democracy — its debates, personalities, and social tensions

• His works contain pointed political satire — would this resonate with Greeks living under Ottoman rule?

• The 1860s saw increasing Greek nationalist sentiment — was classical philology a form of cultural assertion?

2. The Newspaper’s Editors

Your metadata identifies the editors as Σταύρος Βουτυράς (Stavros Voutyras) and Δημήτριος Νικολαΐδης (Dimitrios Nikolaidis). Would you like me to search for more information about these figures and their role in Constantinopolitan Greek intellectual life?

3. The Visual Program

The panoramic engraving of Constantinople in the masthead is striking. Notice how it presents the city’s silhouette — minarets visible, boats on the water (likely the Golden Horn or Bosphorus). This is not an image of ancient Athens, but of their contemporary city. What does this choice suggest about how these Greek intellectuals understood their relationship to place?

---

Sample Transcription and Translation

Let me give you a taste of the content. From the opening of the left column article:

Original (as I read it):

Ἔπαινος τοιοῦτος δὲν εἶναι κατώτερος οὐδ’ αὐτοῦ τοῦ Σοφοκλέους· τῷ ὄντι οἱ δύο οὗτοι ποιηταί, οἱ τοσοῦτον κατ’ ἐπιφάνειαν διάφοροι, ὁ Σοφοκλῆς καὶ Ἀριστοφάνης, ἐχρημάτισαν συγγραφεῖς τῆς αὐτῆς οἰκογενείας...

Literal English:

“Praise such-as-this is not inferior not-even to-that of Sophocles himself; in truth the two these poets, the so-much in appearance different, Sophocles and Aristophanes, served-as writers of-the same family...”

Modernized English:

“Such praise is not inferior even to that accorded Sophocles himself; in truth, these two poets—so different in outward appearance—Sophocles and Aristophanes, were writers of the same family...”

---

Questions for Further Exploration

1. Would you like me to produce a full V3-T analysis of one or both columns, with line-by-line transliteration and translation?

2. Should I search for contextual information about the editors, or about Greek journalism in Ottoman Constantinople during this period?

3. The article references Attic criticism (ἀττικισμός) and discusses whether Aristophanes’ poetry is of “Attic soil” — this touches on 19th-century debates about linguistic purism. Is the Katharevousa/Demotic tension relevant to how you’re thinking about this document?

4. The metadata mentions an insert: “Ο Πλοίαρχος Καλόβολος” by Παύλος Σωνιέρ (Paul Soulier). This appears to be a translation of a French work. Would the presence of translated European literature alongside classical scholarship tell us something about the cultural positioning of this publication?

What direction would you like to take this analysis?

---

In conclusion

Let me encourage you to experiment for yourselves. It is only through personal experimentation, playing with tools and exploring how they may be of use (or not) to you personally as historians that you will be able to judge their utility. Of course this is not the only way to do historical research, but I hope this article has at least awakened your curiosity and experimental instincts.

The topic of the next session of the ai + history collaboratory I convene will be LLM-enabled HTR. Please contact me if you would like to attend as an observer and learn more about the methods I am developing for the Ottoman Archive use case.

Tuesday, January 20th 2025 @ 4 pm UK time; 5 pm Paris, Berlin, Madrid; 11 am EST by ZOOM. Duration = two hours.

---

APPENDICES

Appendix One: Github Repository

I am working on a GitHub repository to support all six Ottoman language HTR projects. I am at the design stage and this has not yet been implemented,

Appendix Two: Project documentation

I have developed a number of documents to record and communicate the work processes and HTR skills files I have developed and continue to develop. These are available to members of the AI + History Collaboratory I convene. Below is an extract from a document named “HTR_Project_Portfolio_Overview_02012026_v5.md” describing the Ottoman Turkish HTR project as part of the portfolio of language projects I am working on.

5. Language Projects Portfolio

5.1 Ottoman Turkish HTR [PRIMARY]

Status: Most developed

Creation Order: 1

Script: Perso-Arabic (RTL)

Period Focus: 1831–1920s

Resource Level: Low

Two-Stage Pipeline: Yes (V3-S-Minimal → V3-T variants)

5.1.1 Historical Context (1830–1920s)

Key Events Affecting Documents and NER:

| Period | Event | Impact on Documents |

|--------|-------|---------------------|

| 1808–1839 | Reign of Sultan Mahmud II | Centralizing reforms; destruction of Janissaries (1826); founding of Takvîm-i Vekâyi (1831) |

| 1839–1876 | Tanzimat Reform Era | Modernization of administration; codification of law; expansion of press; multilingual government publications |

| 1856 | Hatt-ı Hümayun | Reform edict; equality of non-Muslims; relevant for NER of minority officials |

| 1876 | First Ottoman Constitution | Constitutional terminology; parliamentary vocabulary |

| 1876–1909 | Hamidian Era | Press restrictions; censorship vocabulary; exile communities |

| 1908 | Young Turk Revolution | Second Constitutional Period; explosion of press; political party terminology |

| 1914–1918 | World War I | Military vocabulary; Entente/Central Powers terminology; wartime censorship |

| 1918–1922 | Empire’s Collapse | Armistice terminology; occupation vocabulary; nationalist movements |

Linguistic Complexity:

Ottoman Turkish functioned as the bureaucratic lingua franca but the empire operated multilingually. Government documents were routinely translated into Greek, Armenian, Bulgarian, and Arabic, particularly before the Tanzimat reforms. The 1876 Constitution established Ottoman Turkish as the official government language, but the concept of a single “official language” is itself a 19th-century invention associated with nationalism.

Low literacy rates (estimated 2–3% early 19th century, 15% by century’s end) meant that high-register Ottoman Turkish with extensive Arabic and Persian vocabulary was accessible only to educated elites.

5.1.2 Document Types

Official Government Gazette:

| Original Script | Transliteration | English |

|-----------------|-----------------|---------|

| تقویم وقایع | Takvîm-i Vekâyi | Calendar of Events |

- Years published: 1831–1922 (first series 1831–1840; second series 1840–1878; third series 1908–1922)

- Languages: Ottoman Turkish; historical editions also in French, Armenian, Greek, Arabic. Persian versions may have existed.

- Significance: First Ottoman newspaper; no systematic scholarly transliteration or English translation exists for early issues. This research produces genuinely original scholarship.

- Digital Access: Turkish National Library (1841–1919); Wikimedia Commons (1,427 PDF files); IRCICA Farabi Library (complete 7,030 issues)

Major Newspapers of Record (1830s–1920s):

| Original Script | Transliteration | English | Years | Character |

|-----------------|-----------------|---------|-------|-----------|

| طنین | Tanin | Echo | 1908–1925 | Semi-official CUP organ |

| اقدام | İkdam | Perseverance | 1894–1928 | Mass-circulation daily |

| صباح | Sabah | Morning | 1876–1922 | Major daily (Armenian-founded by Mihran Efendi) |

| وقت | Vakit | Time | 1917–1930s | Founded during WWI |

| ترجمان حقیقت | Tercüman-ı Hakîkat | Interpreter of Truth | 1878–1922 | Conservative daily |

| پیام | Peyam | Message | 1913–1914 | Political daily |

French-Language Press (Constantinople):

- Le Stamboul (1875–1962): Leading French daily

- Journal de Constantinople et des Intérêts Orientaux (1843–1930s): Oldest French paper

- La Turquie (1866–1930s)

- Extensive digitization via SALT Research/BnF/IFEA collaboration

Armenian-Language Press (Constantinople):

| Armenian Script | Transliteration | English | Years | Status |

|-----------------|-----------------|---------|-------|--------|

| Ժամանակ | Jamanak | Time | 1908–present | Only major Armenian daily confirmed publishing by November 1917; oldest continuously published Armenian-language daily in the world. Founded October 28, 1908 by Misak and Sarkis Koçunyan. |

| Ազատամարտ | Azadamart | Freedom’s Battle | 1909–1915 | Major ARF newspaper; founded by writer Roupen Zartarian; ceased when staff arrested April 1915 |

Greek-Language Press in Ottoman Constantinople:

| Greek Script | Transliteration | English | Years | Notes |

|--------------|-----------------|---------|-------|-------|

| Ἀνατολικὸς Ἀστήρ | Anatolikos Astēr | Eastern Star | 1861– | Constantinople Greek press |

| Κωνσταντινούπολις | Kōnstantinoupolis | Constantinople | 1867– | “Most widely read Greek paper in the Ottoman Empire” |

5.1.3 Key Linguistic Challenges

- Perso-Arabic script ambiguity (underdotted letters, ligatures)

- Triple linguistic layer (Turkish grammar, Arabic/Persian vocabulary up to 80% in high register)

- Lithographic vs. movable type printing distinctions

- Triple calendar systems (Rumi/Hijri/Gregorian)

- Izafet constructions spanning Arabic, Persian, and Turkish grammatical rules

5.1.4 NER Framework Considerations

| Category | Examples | Notes |

|----------|----------|-------|

| Persons | Sultan Mahmud II, Reşid Paşa, Enver Paşa | Titles and honorifics vary by period |

| Institutions | Bâb-ı Âli, Meclis-i Mebusan, Divan-ı Hümayun | Administrative terminology evolves through reforms |

| Places| Constantinople/Dersaadet, Rumeli, Anatolu | Multiple naming conventions |

| Dates | Rumi, Hijri, Gregorian | Triple calendar system requires conversion |

| Ranks/Titles| Paşa, Bey, Efendi, Kadı | Social hierarchy markers |

| Political Parties | İttihat ve Terakki, Hürriyet ve İtilaf | Post-1908 |

5.1.5 HTR Project Corpus Analysed

- Takvîm-i Vekâyi: Issues 1, 181, 185 (complete transliteration/translation)

- Second Constitutional Period newspapers: Tanin, Peyam

- Personal correspondence: İSAM Archive, Hüseyin Hilmi Paşa Documents

- Administrative documents and chronicles: Şânîzâde Tarihi, Vekâyi-i Devlet-i Aliye

- Cartographic materials: Ottoman Map Text Inventory, Balkans 1890

5.1.6 Protocols Developed

Visual Capture (Stage 1):

- V3-S-Minimal: Core visual capture protocol

- V3-S-Newspaper (v1.0, v1.1, v1.2): Newspaper-specific visual capture

Semantic Processing (Stage 2):

- V3-T: Core transliteration/translation

- V3-T-C: Correspondence variants (Personal, Administrative)

- V3-T-Chronicle: Biographical and historical texts

- V3-T-Newspaper: Second Constitutional Period journalism

1. Colin Greenstreet, ‘A New Lens into the Archive: You are in an archive. You find a document in a language you don’t understand. You take a photo, input it into Gemini 3 Pro. 60 seconds later you have a transcription, transliteration, and translation’, Generative Lives, December 4th 2025, accessed 02/01/2026. Click here.

2. Colin Greenstreet, ‘Mid-C20th Yiddish HTR: The potential for LLM-based transcription is clear, as amateurs and professionals experiment with Gemini 3 Pro’s unique visually grounded capabilities. So how does Gemini perform in an edge case?’, Generative Lives, December 20th 2025, accessed 02/01/2025. Click here.

3. Colin Greenstreet, ‘A New Skill Set for Historians’, Friday, July 19^th 2024. Internal AI seminar at the National Archives, Kew. Seminar slides. Click here.

4. Colin Greenstreet, ‘AI assistants and agents: A New Skill Set for Historians’, Tuesday, November 19^th 2024. IHR Digital History seminar. Youtube video. Click here for recording. Seminar slides. Click here for slides.

5. The ISAM Library was established in Istanbul in 1984 to support the Diyanet Encyclopedia of Islam. Since 2012, but accelerating in 2016 and 2022 ,there has been increasing digitisation, in a project known since 2022 as the “Digitalisation Project”. The ISAM Library Archive (IKA) catalogue entry point: https://arsiv.isam.org.tr/index.php/ika-isam-k-ut-uphanesi-arsivi-15, accessed 04/01/2026

6. The National Library of Greece catalogue entry point. https://catalogue.nlg.gr, accessed 04/01/2026

7. Endangered Archives Scheme run by the British Library in London was established in 2004. It focuses on archival material from before the middle of the 20th century, located in countries where resources for preservation are limited. Digital records are deposited in an appropriate repository in the country of origin, while a secondary copy is held at the British Library for permanent digital preservation and online access. Endangered Archives Scheme catalogue entry point: https://eap.bl.uk/search, accessed 04/01/2026

8. ‘Balkan States’, map from "Stanford's Compendium of Geography and Travel: Europe" Volume 1, 1899 https://maps.lib.utexas.edu/maps/historical/balkan_states_1899.jpg; accessed 29/12/2025

9. ‘Carte Ethnografique de la Macédoine: Point de vue serbe’, Map from “Report of the International Commission To Inquire into the Causes and Conduct of the Balkan Wars” 1914; https://maps.lib.utexas.edu/maps/historical/balkan_serbs_1914.jpg; ‘Carte Ethnografique de la Macédoine: Point de vue bulgare’, Map from “Report of the International Commission To Inquire into the Causes and Conduct of the Balkan Wars” 1914; https://maps.lib.utexas.edu/maps/historical/balkan_bulgarian_1914.jpg ; accessed 29/12/2025

10. ‘Birth certificate Author’s Paternal Grandmother, Arusiak Adamyants born on April 24, 1904 in Shushi. The text is bilingual with Russian on the left. This is an good example of developed writing culture present in Artsakh at the turn of the 20th century as it is executed by an anonymous clerk in the Municipality of Shushi (then part of the Russian Empire). Image: personal archive of Ruben Malayan’, discussed in ‘Historical Background’ webpage on website titled ‘The Art of Armenian Calligraphy by Ruben Malayan’, accessed 03/12/2025. Click here

11. Takvîm-i Vekâyi [Ottoman Government Gazette], Issue 1, 1831. https://upload.wikimedia.org/wikipedia/commons/a/a3/Takvim-i_Vekayi_-_0001.pdf , accessed 26/12/2025

12. Şanizade History by Şanizade Mehmed Ataullah Efendi, 1242/1826 [CE], publication date 1284/1868 [CE]. ISAM. Click here.

13. Sadâret Correspondence (Outgoing to Inspector-General), İSAM Kütüphanesi Arşivi (İKA). Sender: Bâb-ı Âlî / Dâ’ire-i Ṣadâret-i ‘Uẓmâ / Mektûbî Ḳalemi; Recipient: Rûm-ili Vilâyât-ı Şâhâne Müfettişliği (Hüseyin Hilmi Paşa); Date: 22 Kânûn-ı Evvel 1319 [Rumi], 4 January 1904 [Gregorian]; p.1 of 2. [INSERT DATA]

14. БАЛКАНЪ [БАЛКАН; Balkan], Year I — Ruse, 10 June 1898 [O.S.] — Issue 7, St. Cyril and Methodius National Library of Bulgaria, republished by the British Library Endangered Archives project, EAP 698/1/8; https://eap.bl.uk/archive-file/EAP696-1-8#?open=true&xywh=-2833%2C-1%2C8710%2C4489&cv=; accessed 30/12/2025

15. Handwritten pre-orthographic reform Bulgarian cyrillic. July 3, 1905. ISAM: IKA HHP-H-2-b-dos.1-1396. p.3 of 24 page composite pdf containing 11 documents. https://arsiv.isam.org.tr/index.php/bulgaristan-gazetelerine-gonderilen-hezeyannameler, accessed 04/01/2026

16. ΕΠΤΑΛΟΦΟΣ ΝΕΑ - “Heptalophos Nea” (Seven-Hilled News), Issue 20, October 31st 1865, p.1; https://medusa.libver.gr/iguana/www.main.cls?surl=search&p=2cafc322-e6e4-433a-9fcf-b8b0e4d5c7da#recordId=3.7076, accessed 03/01/2026

17. Drita [The Light], January 1st 1908, Issue 95, p.1 of 4 (whole issue = pp.1-4). Published Sofia, Bulgaria. Albanian romanised script; Ottoman script. Sourced from ISAM (İslam Araştırmaları Merkezi / Centre for Islamic Studies). Fonds: Hüseyin Hilmi Pasha Documents; sub-fonds: Rumelia Inspectorate; series: Foreign activities and the foreign press in the Balkans; sub-series: Foreign Press; file: Macedonia issue; item number: 0621 IKA HHP-H-2-b-dos.1-0621.

18. ‘Birth certificate Author’s Paternal Grandmother, Arusiak Adamyants born on April 24, 1904 in Shushi. The text is bilingual with Russian on the left. This is an good example of developed writing culture present in Artsakh at the turn of the 20th century as it is executed by an anonymous clerk in the Municipality of Shushi (then part of the Russian Empire). Image: personal archive of Ruben Malayan’, discussed in ‘Historical Background’ webpage on website titled ‘The Art of Armenian Calligraphy by Ruben Malayan’, accessed 03/12/2025. Click [here]

19. I introduced the idea of skills.md files and HTR-skills.md files in the final section of my article on Mid-C20th Yiddish HTR titled ‘Agentic and Skills Framework’, and demonstrated a Yiddish HTR skills.md file I had developed for use with a specific 1940s’s Yiddish hand. See Colin Greenstreet, ‘Mid-C20th Yiddish HTR, Generative Lives, December 20th 2025, accessed 02/01/2025. Click here.

20. Ἑφημερίς τῆς Κυβερνήσεως, Greek Government Gazette, 14 Ἰανουαρίου 1833 [Julian], 26 January 1833 [Gregrorian], Issue 1. The front page of the first issue with the proclamation of King Otto to the Greek people, 1833; https://en.wikipedia.org/wiki/Government_Gazette_(Greece)#/media/File:Efimerida_tis_kiberniseos.JPG ; accessed 01/01/2026; Gemini 3 Pro Preview and Claude Opus 4.5, prompted by Colin Greenstreet, accessed

21. V3-T-Greek skills markdown file extract, Claude Opus 4.5 in Claude Greek HTR project, prompted by Colin Greenstreet

22. Claude Greek HTR project

23. Peyam newspaper. p.1 of the 14 Ağustos 1335 (Rumi)/August 14, 1919 (Gregorian) issue. Visual capture by Gemini 3 Pro using V3-S-Minimal. Semantic processing of transliteration, transclation, NER and contextual sumamrisation by Claude Opus 4.5 usingV3-T Protocol, December 20th 2025.

24. Ottoman War Staff Map. ca. 1890. CCBY4. https://commons.wikimedia.org/wiki/Category:Ottoman_Turkish-language_maps#/media/File:1890_map_of_Turkey_in_Europe_in_Ottoman_Turkish.jpg ; : https://www.digitale-sammlungen.de/en/view/bsb00005840?page=1 accessed 29/12/2025

25. Extract from Ottoman War Staff Map. ca. 1890. CCBY4. https://commons.wikimedia.org/wiki/Category:Ottoman_Turkish-language_maps#/media/File:1890_map_of_Turkey_in_Europe_in_Ottoman_Turkish.jpg ; : https://www.digitale-sammlungen.de/en/view/bsb00005840?page=1 accessed 29/12/2025

26. See Appendix One: GitHub Repository

27. See Aurelius-Archives [Updated Oct 2025], a bespoke ChatGPT which “helps historians interrogate research resources and metadata provided by archives and libraries worldwide”. Discussed in Colin Greenstreet, ‘A New Skill Set for Historians’, Friday, July 19^th 2024. Internal AI seminar at the National Archives, Kew.’ Seminar slides. pp. 6-9.