Triple

T13257275
Position Surface form Disambiguated ID Type / Status
Subject Howard Cosell E315690 entity
Predicate familyName P18 FINISHED
Object Cosell E315690 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: Cosell | Statement: [Howard Cosell, familyName, Cosell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cosell
Context triple: [Howard Cosell, familyName, Cosell]
  • A. Cosell chosen
    Cosell is the surname of Howard Cosell, the influential and outspoken American sports journalist and broadcaster best known for his work on Monday Night Football.
  • B. Cohon
    Cohon is the family surname of American actor, author, and narrator Peter Coyote, born Peter Cohon.
  • C. Cosey
    Cosey is a surname most notably associated with the character Bill Cosey from Toni Morrison’s novel "Love."
  • D. Honi Coles
    Honi Coles was an acclaimed American tap dancer and choreographer renowned for his elegance, speed, and precision, and for helping to preserve and advance the jazz tap tradition.
  • E. Sossick
    Sossick is a Nigerian music producer known for crafting influential hip-hop and Afrobeats tracks for prominent artists.
  • 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_69d806b1d9ac8190852c5571d5bd5f0f completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98f7614fc8190a1cac076d706e9aa completed April 11, 2026, 12:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69f70a4240d881909f0ee898fd272826 completed May 3, 2026, 8:41 a.m.
Created at: April 9, 2026, 9:25 p.m.