Triple

T12512271
Position Surface form Disambiguated ID Type / Status
Subject Jermain Taylor E299107 entity
Predicate notableOpponent P893 FINISHED
Object Kelly Pavlik E295269 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: Kelly Pavlik | Statement: [Jermain Taylor, notableOpponent, Kelly Pavlik]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelly Pavlik
Context triple: [Jermain Taylor, notableOpponent, Kelly Pavlik]
  • A. Kelly Pavlik chosen
    Kelly Pavlik is an American former professional boxer and unified middleweight world champion known for his power punching and notable fights in the 2000s.
  • B. Amir Tyson
    Amir Tyson is an American media personality and entrepreneur best known as the son of former heavyweight boxing champion Mike Tyson.
  • C. Cory Spinks
    Cory Spinks is an American former professional boxer and multiple-time world champion, best known for unifying the welterweight titles and being the son of heavyweight champion Leon Spinks.
  • D. Chad Dawson
    Chad Dawson is an American professional boxer best known for his reign as a world light heavyweight champion and victories over several elite fighters in the division.
  • E. Guy Kibbee
    Guy Kibbee was an American character actor best known for his affable, often comical supporting roles in 1930s and 1940s Hollywood films.
  • 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_69d6ada4cd388190ae3bbf83ff87057a completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9541d6e508190a4992f328e077467 completed April 10, 2026, 7:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bbba5fc819082a4171a5a77183a completed May 2, 2026, 7:08 p.m.
Created at: April 8, 2026, 9:57 p.m.