Triple

T18819149
Position Surface form Disambiguated ID Type / Status
Subject I'll Fly for You E460215 entity
Predicate producer P490 FINISHED
Object Tony Swain 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: Tony Swain | Statement: [I'll Fly for You, producer, Tony Swain]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Swain
Context triple: [I'll Fly for You, producer, Tony Swain]
  • A. Tony Swain chosen
    Tony Swain is a British songwriter and record producer best known for his work on numerous 1980s pop hits, often in collaboration with Steve Jolley.
  • B. Sam Swainsbury
    Sam Swainsbury is a British actor best known for his role as Jason in the BBC sitcom "Mum" and appearances in various UK television dramas and comedies.
  • C. Terry Swinton
    Terry Swinton is an author whose work about boxer Rubin "Hurricane" Carter served as the basis for the 1999 film "The Hurricane."
  • D. Michael Gwynn
    Michael Gwynn was a British character actor known for his roles in mid-20th-century film and television, including appearances in classic horror and science fiction productions.
  • E. Clive Griffin
    Clive Griffin is a British pop and soul singer best known for his 1993 duet "When I Fall in Love" with Celine Dion from the film Sleepless in Seattle.
  • 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_69d8dcf94c288190a06dea029ae4b223 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5a6b8b7d88190a8828746176776ea completed April 20, 2026, 4:08 a.m.
Created at: April 10, 2026, 11:55 a.m.