Triple

T8534441
Position Surface form Disambiguated ID Type / Status
Subject Carol Creighton Burnett E202041 entity
Predicate spouse P13 FINISHED
Object Don Saroyan E92546 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 Saroyan | Statement: [Carol Creighton Burnett, spouse, Don Saroyan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Saroyan
Context triple: [Carol Creighton Burnett, spouse, Don Saroyan]
  • A. Don Saroyan chosen
    Don Saroyan was an American actor and television producer best known for his marriage to comedian and actress Carol Burnett.
  • B. Hal Mohr
    Hal Mohr was an American cinematographer renowned for his innovative camera work in early Hollywood, notably becoming the only write-in Academy Award winner for his cinematography.
  • C. Dick Van Patten
    Dick Van Patten was an American actor best known for his role as the father on the television series "Eight Is Enough" and for numerous character roles in film and TV comedies.
  • D. George Bergman
    George Bergman was an American mathematician known for his work in algebra and category theory and for his influential contributions to mathematical education and expository writing.
  • E. Kevin Kiner
    Kevin Kiner is an American composer best known for his prolific work on film and television scores, including major franchises like Star Wars and DC Comics adaptations.
  • 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_69ca832355b08190b8b6a4ab4a4a3554 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe6a0ccd4819097b41d0dfb1c5018 completed March 31, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d7aa3a881909bfdd3536dbc4ec7 completed April 2, 2026, 1:22 p.m.
Created at: March 30, 2026, 6:17 p.m.