glam/data
kempersc d51bba5003 data: update entity resolution confidence scores
Regenerated confidence scores with updated scoring algorithm:
- Total candidates: 78,746
- Adjusted: 2,832 (was 3,869)
- Boosted: 2,499 (was 3,192)
- Penalized: 333 (was 677)
- Likely wrong person: 533
- Reviews preserved: 57

Confidence scoring version: 2.0
2026-01-13 21:54:18 +01:00
..
custodian
custodian.backup.20251230
custodian_sample
entity_annotation
entity_resolution data: update entity resolution confidence scores 2026-01-13 21:54:18 +01:00
examples
extracted
google_maps_enrichment
instances
intangible_heritage
isil
json
jsonld
manual_enrichment
museum_register_nl
nde
ontology edit slots 2026-01-13 20:35:11 +01:00
person enrich person profiles 2026-01-11 18:08:40 +01:00
rag_eval
raw
rdf
reference
reports
review
test
training
unified
validation
web/lap_gaza_report_2024
wikidata
wikpedia/Destruction_of_cultural_heritage_during_the_Israeli_invasion_of_the_Gaza_Strip
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
failed_crawl_urls.txt
failed_crawl_urls_round1_backup.txt
failed_crawl_urls_round3_backup.txt
failed_crawl_urls_round4.txt
ISIL-codes_2025-08-01.csv
linkedin_locations.json
mexican_geography_analysis.yaml
missing_annotations_checkpoint.json
NDE-logo-RGB-basis-nl-blauw.png
reenrich_queue.json
sparql_templates.yaml
temp_conv1_artifact2.md
temp_conv2_artifact1.md
temp_mexican_conv1.json
temp_mexican_conv2.json
unenriched_urls_round2.txt
wcms_migration_state.json centralise slots 2026-01-12 14:33:56 +01:00
xxx_matches.json