Codesota · Benchmark · AIDA-CoNLLHome/Leaderboards/Language & Knowledge/Entity Linking/AIDA-CoNLL
Unknown

AIDA-CoNLL.

Entity linking benchmark built on CoNLL 2003 NER data with YAGO2 entity annotations. Standard test-b split used for in-KB Micro-F1 / accuracy evaluation.

Paper ↗Leaderboard ↓
§ 01 · Leaderboard

Results by metric.

Only 3 models on this benchmark
Help build the community leaderboard — submit your model results.
Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result ↗Report issue ↗

Micro F1

Micro F1 is the reported evaluation metric for AIDA-CoNLL. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Micro F1verifiedpapervendorcommunityunverified
RankModelTrustScoreYearLinksFix
01GENRE
GENRE in-KB accuracy / Micro-F1 on AIDA-CoNLL test-b. seed — verify
paper93.32026Source ↗Looks wrong?
02SpEL-large
SpEL-large on AIDA-CoNLL test InKB Micro-F1. seed — verify
paper92.72026Source ↗Looks wrong?
03ReFinED
ReFinED on AIDA-CoNLL test-b InKB Micro-F1. seed — verify
paper86.62026Source ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Entity Linking