Commit graph

12 commits

Author SHA1 Message Date
kempersc
1635625032 added web annotations 2025-12-06 19:50:04 +01:00
kempersc
55e2cd2340 feat: implement LLM-based extraction for Archives Lab content
- Introduced `llm_extract_archiveslab.py` script for entity and relationship extraction using LLMAnnotator with GLAM-NER v1.7.0.
- Replaced regex-based extraction with generative LLM inference.
- Added functions for loading markdown content, converting annotation sessions to dictionaries, and generating extraction statistics.
- Implemented comprehensive logging of extraction results, including counts of entities, relationships, and specific types like heritage institutions and persons.
- Results and statistics are saved in JSON format for further analysis.
2025-12-05 23:16:21 +01:00
kempersc
4da64eeebf improve annotator 2025-12-05 16:25:39 +01:00
kempersc
e38fb4613b improve annotation prompt 2025-12-05 15:51:39 +01:00
kempersc
3a242370fc annotation standards added 2025-12-05 15:30:23 +01:00
kempersc
d661947830 update enriched entries 2025-12-03 17:38:46 +01:00
kempersc
097d116b72 enrich entries 2025-12-01 16:06:34 +01:00
kempersc
f3c149b1bb update entries 2025-11-30 23:30:29 +01:00
kempersc
d623f0af4a store archived websites 2025-11-29 20:40:46 +01:00
kempersc
572ccd5daf archive websites 2025-11-29 18:18:04 +01:00
kempersc
0ab8f24a6b archive websites 2025-11-29 18:05:16 +01:00
kempersc
da1eae6597 Refactor code structure for improved readability and maintainability 2025-11-29 12:27:39 +01:00