Triple

T10357279
Position Surface form Disambiguated ID Type / Status
Subject Don Bachardy E244029 entity
Predicate name P16 FINISHED
Object Don Bachardy E244029 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: Don Bachardy | Statement: [Don Bachardy, name, Don Bachardy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Bachardy
Context triple: [Don Bachardy, name, Don Bachardy]
  • A. Don Bachardy chosen
    Don Bachardy is an American portrait artist known for his long-term relationship with writer Christopher Isherwood and his distinctive drawings of notable cultural figures.
  • B. Bernie Ulman
    Bernie Ulman was a prominent American football official best known for serving as a referee in the National Football League, including officiating major games such as Super Bowl IX.
  • C. Gil Cates
    Gil Cates was an American film, television, and theater producer and director best known for his multiple stints producing the Academy Awards telecasts.
  • D. Donald Kushner
    Donald Kushner is an American film producer best known for producing the groundbreaking science-fiction film "Tron" (1982).
  • E. Paul Rubell
    Paul Rubell is an American film editor known for his work on high-profile movies such as "The Insider," "Collateral," and "Transformers."
  • 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_69d381b22b8c8190aaed476be5f872a9 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e9563ea48190b8702b3ef497ed9a completed April 7, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69d750b02ae48190898f9f97ab19ce60 completed April 9, 2026, 7:09 a.m.
Created at: April 6, 2026, 11:58 a.m.