Triple

T8767050
Position Surface form Disambiguated ID Type / Status
Subject Larry Holmes vs. Muhammad Ali E208362 entity
Predicate undercardNotable P85276 FINISHED
Object Earnie Shavers vs. Bernardo Mercado 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: Earnie Shavers vs. Bernardo Mercado | Statement: [Larry Holmes vs. Muhammad Ali, undercardNotable, Earnie Shavers vs. Bernardo Mercado]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: undercardNotable
Context triple: [Larry Holmes vs. Muhammad Ali, undercardNotable, Earnie Shavers vs. Bernardo Mercado]
  • A. under
    Indicates that one entity is positioned below or beneath another entity, often implying vertical alignment or coverage.
  • B. notableSingle
    Indicates that the subject is particularly recognized or distinguished for one specific, individual instance (such as a single work, event, or achievement).
  • C. notableAce
    Indicates that one entity is a particularly distinguished or outstanding example (an “ace”) within the domain or activity associated with the other entity.
  • D. notableFor
    Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
  • E. notableArc
    Indicates a significant or defining narrative development, transformation, or storyline involving the related entities.
  • F. None of above. chosen

Provenance (4 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_69ca835df7e08190ac875664cca8f9ca completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5eeae70c8190adc2bc2846da0fbf completed March 31, 2026, 11:55 p.m.
PD Predicate disambiguation batch_69cc5c1884bc8190a46e8308db31f7ab completed March 31, 2026, 11:43 p.m.
PDg Predicate description generation batch_69cc5cfddef48190aee764ee7b25bae9 completed March 31, 2026, 11:47 p.m.
Created at: March 30, 2026, 6:41 p.m.