Triple

T22099981
Position Surface form Disambiguated ID Type / Status
Subject Johnny Dankworth E546142 entity
Predicate workedWith P398 FINISHED
Object Peter King 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: Peter King | Statement: [Johnny Dankworth, workedWith, Peter King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peter King
Context triple: [Johnny Dankworth, workedWith, Peter King]
  • A. Peter King
    Peter King is a prominent American sportswriter and television analyst best known for his long-running NFL coverage and insider reporting.
  • B. Peter King chosen
    Peter King is a British Conservative politician who served as the Member of Parliament for Bridgwater and later Bridgwater and West Somerset.
  • C. Bill Pope
    Bill Pope is an acclaimed American cinematographer best known for his dynamic, visually inventive work on major films such as The Matrix trilogy and the Spider-Man series.
  • D. Rob Pope
    Rob Pope is an American bassist best known for his work with the emo and indie rock band The Get Up Kids.
  • E. Bill King
    Bill King was a renowned American sportscaster best known for his distinctive play-by-play calls for Bay Area teams including the Oakland A’s, Golden State Warriors, and Oakland/Los Angeles Raiders.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1291440048190992c48893ced0b34 completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.