Triple

T11760103
Position Surface form Disambiguated ID Type / Status
Subject Sullivan & Son E279631 entity
Predicate executiveProducer P7225 FINISHED
Object Steve Byrne E943748 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: Steve Byrne | Statement: [Sullivan & Son, executiveProducer, Steve Byrne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steve Byrne
Context triple: [Sullivan & Son, executiveProducer, Steve Byrne]
  • A. Steve Byrne chosen
    Steve Byrne is an American stand-up comedian and actor best known for creating and starring in the TBS sitcom "Sullivan & Son."
  • B. Peter Byrne
    Peter Byrne was a British actor best known for his long-running role as Andy Crawford in the classic television police series "Dixon of Dock Green."
  • C. Roger Byrne
    Roger Byrne was an English footballer who captained Manchester United's famed "Busby Babes" side in the 1950s.
  • D. Larry Byrne
    Larry Byrne is the husband of American politician Leslie L. Byrne, who served as a U.S. Representative from Virginia.
  • E. Michael Byrne
    Michael Byrne is a British character actor known for his numerous film and television roles, often portraying military officers or authority figures.
  • 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_69d6ab01038c819080714901502c84fc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a52386708190b744746a2db37495 completed April 10, 2026, 7:22 a.m.
NED1 Entity disambiguation (via context triple) batch_69f1309f25a88190b0acaf7d9be6ae59 completed April 28, 2026, 10:11 p.m.
Created at: April 8, 2026, 9:41 p.m.