Triple

T23165902
Position Surface form Disambiguated ID Type / Status
Subject Kamaru Usman E578709 entity
Predicate team P3756 FINISHED
Object Sanford MMA NE NERFINISHED

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: Sanford MMA | Statement: [Kamaru Usman, team, Sanford MMA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanford MMA
Context triple: [Kamaru Usman, team, Sanford MMA]
  • A. Sanford MMA chosen
    Sanford MMA is a prominent mixed martial arts training gym known for developing elite UFC fighters and world champions.
  • B. Mjölnir MMA
    Mjölnir MMA is an Icelandic mixed martial arts gym and training team known for producing high-level fighters such as UFC welterweight Gunnar Nelson.
  • C. Wolfslair MMA Academy
    Wolfslair MMA Academy is a British mixed martial arts training camp known for coaching several prominent UFC and Bellator fighters.
  • D. Kings MMA
    Kings MMA is a renowned mixed martial arts gym and fight team based in Southern California, known for producing elite UFC and Bellator fighters under coach Rafael Cordeiro.
  • E. Black House MMA
    Black House MMA is a renowned mixed martial arts training camp and gym known for developing high-level professional fighters, particularly in Brazil.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245fc75348190a0288401044c8af8 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18f2bca4881909f6148d588948018 completed April 29, 2026, 4:55 a.m.
Created at: April 17, 2026, 4:03 p.m.