Triple

T7204162
Position Surface form Disambiguated ID Type / Status
Subject Joe Burrow E148622 entity
Predicate awardReceived P11 FINISHED
Object Heisman Trophy E129967 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: Heisman Trophy | Statement: [Joe Burrow, awardReceived, Heisman Trophy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heisman Trophy
Context triple: [Joe Burrow, awardReceived, Heisman Trophy]
  • A. Heisman Trophy chosen
    The Heisman Trophy is college football’s most prestigious individual award, given annually to the most outstanding player in NCAA Division I.
  • B. Lombardi Award
    The Lombardi Award is a prestigious college football honor presented annually to the nation’s top lineman or linebacker who exemplifies outstanding performance, leadership, and character.
  • C. Davey O'Brien Award
    The Davey O'Brien Award is a prestigious annual college football honor given to the nation's top quarterback in the United States.
  • D. Walter Camp Award
    The Walter Camp Award is a prestigious annual college football honor presented to the nation's most outstanding player, as selected by the Walter Camp Football Foundation.
  • E. Lou Groza Award
    The Lou Groza Award is an annual college football honor presented to the top placekicker in the United States.
  • 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_69c687e8cf188190b5f3ecffd681f04e completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6e94bfb2c81909ab492757435fce4 completed March 27, 2026, 8:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7bfbb7564819091ce3669380409a1 completed March 28, 2026, 11:47 a.m.
Created at: March 27, 2026, 2:52 p.m.