Entity extraction
Find people, places, texts, deities, dates and other named entities.
Definition
Finding named entities in a text and classifying them (person, place, text, deity, monastery, date), ideally linking each to an authority record such as a BDRC or other database ID.
Input and output
- Input: A text.
- Output: A list of entity mentions with type, position and, where possible, an authority ID.
Examples
None yet. Add a short real example with its correct answer, and say where it comes from.
Edge cases
- The same person under many names and titles.
- Dates in the Tibetan calendar or coded as words.
- Deity names that are also ordinary words.
- Author names in colophons.
Languages and traditions
- Tibetan (bo): one team has an author-name detection skill and benchmark set (team call, 2026-11-17).
How it is measured
No benchmark yet: help build one. See below.
Help wanted
Texts with entities marked and linked by a human reader. A first benchmark can be small: twenty to fifty items. See how to submit a benchmark.
Related tasks
Found in workflows
- Preparing a digital edition from a template repo (Sitar)
- Translating a Buddhist text (Kurt Keutzer)

BuddhistAI Knowledge base