Triple

T27286852
Position Surface form Disambiguated ID Type / Status
Subject Randy Turpin E688499 entity
Predicate rematchResult P56461 FINISHED
Object lost to Sugar Ray Robinson by technical knockout LITERAL 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: lost to Sugar Ray Robinson by technical knockout | Statement: [Randy Turpin, rematchResult, lost to Sugar Ray Robinson by technical knockout]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: rematchResult
Context triple: [Randy Turpin, rematchResult, lost to Sugar Ray Robinson by technical knockout]
  • A. rematchDate
    Indicates the date on which a subsequent or repeat contest between the same parties is scheduled or took place.
  • B. isRematchOfFinal
    Indicates that a match is a subsequent encounter replaying the same opponents and stakes as a previous final match.
  • C. wasRematchOf
    Indicates that an event or contest is a subsequent encounter between the same parties, held as a repeat of a previous matchup.
  • D. resultOfMatch chosen
    Indicates that one entity is the outcome or product produced by a particular match or matching event involving another entity.
  • E. replayResult
    Indicates that an outcome or state is produced as a consequence of replaying a prior event, action, or sequence.
  • F. None of above.

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_69ef355998e08190bdff849e8f33adce completed April 27, 2026, 10:07 a.m.
NER Named-entity recognition batch_69f627565c688190a8f4f9fd9ce84990 completed May 2, 2026, 4:33 p.m.
PD Predicate disambiguation batch_69f623a91b9c8190b2e2fdbc55cb89b6 completed May 2, 2026, 4:17 p.m.
Created at: April 27, 2026, 11:12 a.m.