Triple

T22918114
Position Surface form Disambiguated ID Type / Status
Subject Jake Paul E568785 entity
Predicate hasFought P30824 FINISHED
Object Tyron Woodley 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: Tyron Woodley | Statement: [Jake Paul, hasFought, Tyron Woodley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tyron Woodley
Context triple: [Jake Paul, hasFought, Tyron Woodley]
  • A. Tyron Woodley chosen
    Tyron Woodley is an American mixed martial artist and former UFC Welterweight Champion known for his explosive power and wrestling-based fighting style.
  • B. Ryan Burnett
    Ryan Burnett is a Northern Irish former professional boxer who held multiple bantamweight world titles during his career.
  • C. Jeremy Ray Taylor
    Jeremy Ray Taylor is an American actor best known for his role as Ben Hanscom in the 2017 horror film adaptation of Stephen King's "It."
  • D. Terence Crawford
    Terence Crawford is an American professional boxer widely regarded as one of the best pound-for-pound fighters of his era, known for his elite technical skill, switch-hitting ability, and multiple world titles across three weight divisions.
  • E. Lucas Matthysse
    Lucas Matthysse is an Argentine former professional boxer known for his formidable punching power and reign as a world light-welterweight champion.
  • 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_69e2458d90c88190a58cead4e781ca6a completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1807b254c8190bb84596dcacaa35e completed April 29, 2026, 3:52 a.m.
Created at: April 17, 2026, 3:42 p.m.