55e2cd2340
- 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. |
||
|---|---|---|
| .. | ||
| entity_annotation | ||
| examples | ||
| extracted | ||
| instances | ||
| intangible_heritage | ||
| isil | ||
| jsonld | ||
| manual_enrichment | ||
| museum_register_nl | ||
| nde | ||
| ontology | ||
| raw | ||
| rdf | ||
| reference | ||
| review | ||
| unified | ||
| wikidata | ||
| collision_edge_case_analysis.md | ||
| deduplication_improvement_summary.md | ||
| dutch_collision_report.txt | ||
| dutch_collision_stats.json | ||
| dutch_deduplication_report.txt | ||
| dutch_institutions_with_ghcids.yaml | ||
| extraction_checkpoint.json | ||
| ISIL-codes_2025-08-01.csv | ||
| mexican_geography_analysis.yaml | ||
| NDE-logo-RGB-basis-nl-blauw.png | ||
| temp_conv1_artifact2.md | ||
| temp_conv2_artifact1.md | ||
| temp_mexican_conv1.json | ||
| temp_mexican_conv2.json | ||
