Triple

T16839905
Position Surface form Disambiguated ID Type / Status
Subject FC Marmande 47 E409380 entity
Predicate fullName P16 FINISHED
Object Football Club Marmande 47 E409380 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Football Club Marmande 47 | Statement: [FC Marmande 47, fullName, Football Club Marmande 47]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Football Club Marmande 47
Context triple: [FC Marmande 47, fullName, Football Club Marmande 47]
  • A. FC Marmande 47 chosen
    FC Marmande 47 is a French football club based in the town of Marmande in the Lot-et-Garonne department.
  • B. Montluçon Football
    Montluçon Football is a French association football club based in the town of Montluçon, competing in the lower tiers of the national league system.
  • C. Stade Bordelais
    Stade Bordelais is a French sports club best known for its rugby union team based in Bordeaux.
  • D. Montpellier HSC
    Montpellier HSC is a French professional football club based in Montpellier that competes in Ligue 1 and has a history of developing notable players such as Eric Cantona.
  • E. Castres Olympique
    Castres Olympique is a professional French rugby union club based in Castres that competes in the country’s top division, the Top 14.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d883952b048190887740a980b712ed completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b34f902c8190a334ba7caa04ce7e completed April 18, 2026, 4:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00bb177e288190b525e6d239892d26 completed May 10, 2026, 5:06 p.m.
Created at: April 10, 2026, 5:23 a.m.