Triple

T13481079
Position Surface form Disambiguated ID Type / Status
Subject Ray Mercer E318371 entity
Predicate fought P30824 FINISHED
Object Tim Witherspoon E601532 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: Tim Witherspoon | Statement: [Ray Mercer, fought, Tim Witherspoon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tim Witherspoon
Context triple: [Ray Mercer, fought, Tim Witherspoon]
  • A. Tim Witherspoon chosen
    Tim Witherspoon is an American former professional boxer and two-time WBC and WBA heavyweight world champion who competed from the late 1970s to the mid-1990s.
  • B. Wayland Holyfield
    Wayland Holyfield is an American country music songwriter known for penning numerous hits for major artists and contributing significantly to the genre’s modern repertoire.
  • C. Ray Ricord
    Ray Ricord is a television producer best known for his executive production work on the drama series "StartUp."
  • D. Aaron Pryor
    Aaron Pryor was an American professional boxer and Hall of Famer best known as a dominant, all-action light welterweight champion during the early 1980s.
  • E. Thomas Hearns
    Thomas Hearns is an American boxing legend known for his devastating punching power, multiple world titles across different weight classes, and classic battles in the 1980s against fellow greats like Sugar Ray Leonard and Marvin Hagler.
  • 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_69d806b6bfec819089222715b2e86c8e completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaf36c6b08190ba99400600e0b662 completed April 12, 2026, 2:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d8c942481909858e340944ed57c completed May 3, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:42 p.m.