Triple

T2594508
Position Surface form Disambiguated ID Type / Status
Subject Muhammad Ali E58195 entity
Predicate influenced P9 FINISHED
Object Mike Tyson E58450 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: Mike Tyson | Statement: [Muhammad Ali, influenced, Mike Tyson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Tyson
Context triple: [Muhammad Ali, influenced, Mike Tyson]
  • A. Mike Tyson chosen
    Mike Tyson is a former American heavyweight boxing champion renowned for his explosive power, intimidating style, and status as one of the most famous and controversial figures in boxing history.
  • B. Tyson
    Tyson is a character in the musical and film "Black Nativity," contributing to its contemporary retelling of the Nativity story through a modern African-American lens.
  • C. Tyson
    Tyson is the surname of Neil deGrasse Tyson, the prominent American astrophysicist, author, and science communicator.
  • D. Evander Holyfield
    Evander Holyfield is an American former professional boxer and undisputed cruiserweight and heavyweight champion, best known for his epic bouts with Mike Tyson and Riddick Bowe.
  • E. Pernell Whitaker
    Pernell Whitaker was an American boxing great renowned for his exceptional defensive skills and multiple world championships across several weight classes.
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd427f58c8190af1c1a9724158c96 completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69afaf3f4c2c8190b9e91b30068bb1c5 completed March 10, 2026, 5:42 a.m.
Created at: March 6, 2026, 9:49 p.m.