-
Notifications
You must be signed in to change notification settings - Fork 0
Home
Metadata
Author: Claude Opus 4.6 in Claude Ottoman Turkish Project, prompted and edited by Colin Greenstreet | Wiki entry created: Sunday, February 8th 2026
Version: v1.3
Version history:
- v1.0 (8 February 2026): Initial draft.
- v1.1 (8 February 2026): Minor text edits; added collapsing metadata feature; changed contact address.
- v1.2 (9 February 2026): Adjusted number of language projects to five from six; reordered and edited material.
- v1.3 (10 February 2026): Minor text edits.
Validation: This wiki entry has been validated by Colin Greenstreet.
This wiki documents the Opening the Ottoman Archive initiative — a collaborative effort to develop, test, and validate large language model based methods for machine transcription and analysis of Ottoman language documents. Our focus is on handwritten manuscripts from the C16th to early C20th in the Ottoman Empire and its successor states.
The initiative spans five language projects — Ottoman Turkish, Albanian, Bulgarian, Greek, and Armenian — reflecting the multilingual reality of the Ottoman Empire. Our focus for the next six months is on Ottoman Turkish, which is the most extensively developed project and the subject of this wiki.
The initiative is working with Ottoman Turkish and other Ottoman-language scholars to co-develop reusable skill files and to explore how they can be integrated into historical research workflows to assist high-quality academic scholarship.
The core methodology uses a two-stage pipeline separating visual capture from semantic processing, with skill files encoding instructions for different document types, genres, scripts, and periods. All skill files are in markdown format and are being developed for the Commons.
Start with the Project introduction for the methodology, or browse by topic:
Typology — how we classify documents:
Pipeline — how we process them:
See HTR/OCR landscape for a survey of existing Ottoman HTR and OCR initiatives, or Demonstration skill files for published examples.
Contact me directly at colin.greenstreet@marinelives.org for a copy of any skill file. I would be delighted to work with you to explore your manuscript or printed use case and to help tailor a skill file or files to fit your own research needs. What excites me is to see other researchers use and further develop these ideas and produce innovative research for the Commons.
Last updated: 9 February 2026 · v1.3
ottoman-archive wiki