Triple

T25219729
Position Surface form Disambiguated ID Type / Status
Subject WBA (Super) lightweight title E631927 entity
Predicate winMethod P151809 FINISHED
Object points decision LITERAL 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: points decision | Statement: [WBA (Super) lightweight title, winMethod, points decision]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: winMethod
Context triple: [WBA (Super) lightweight title, winMethod, points decision]
  • A. winnerSelectionMethod
    Indicates the process or criteria used to determine which participant is chosen as the winner.
  • B. wonFor
    Indicates that one entity received an award, prize, or recognition specifically on behalf of or representing another entity.
  • C. mmaWinMethod chosen
    Indicates the method or manner by which a fighter wins an MMA bout (e.g., knockout, submission, decision).
  • D. winsFor
    Indicates that one entity achieves victory or success on behalf of, or in favor of, another entity.
  • E. wonBy
    Indicates that a contest, game, or competition is decided in favor of a particular participant or side.
  • F. None of above.

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_69e75a8e0f688190a7aebe9a4815e25b completed April 21, 2026, 11:07 a.m.
NER Named-entity recognition batch_69f47b914fe08190b104ecc2583ce1f7 completed May 1, 2026, 10:08 a.m.
PD Predicate disambiguation batch_69f44d849e7c81909945438f40e35362 completed May 1, 2026, 6:51 a.m.
Created at: April 21, 2026, 1:02 p.m.