Triple

T16107839
Position Surface form Disambiguated ID Type / Status
Subject Ray Peterson E390785 entity
Predicate spouse P13 FINISHED
Object Carol Peterson 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: Carol Peterson | Statement: [Ray Peterson, spouse, Carol Peterson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carol Peterson
Context triple: [Ray Peterson, spouse, Carol Peterson]
  • A. Carol Peterson chosen
    Carol Peterson is a suburban housewife and the suspicious, strong-willed wife of Ray Peterson in the dark comedy film "The 'Burbs."
  • B. Elizabeth Peterson
    Elizabeth Peterson is an actress known for her role in the fantasy action film "Avengers Grimm."
  • C. Sylvia Peterson
    Sylvia Peterson is an American singer best known as a member of the 1960s girl group The Chiffons, who had hits like "He's So Fine" and "One Fine Day."
  • D. Sally Peterson
    Sally Peterson is known as the spouse of American investment banker and former U.S. Secretary of Commerce Peter G. Peterson.
  • E. Dorothy Peterson
    Dorothy Peterson was an American character actress active in the early to mid-20th century, known for her numerous supporting roles in Hollywood films.
  • 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_69d87f1a8dd881909f1de6ef78849874 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e1ff6e55c08190b77f344e4e8c42ad completed April 17, 2026, 9:37 a.m.
Created at: April 10, 2026, 5 a.m.