Triple

T21432194
Position Surface form Disambiguated ID Type / Status
Subject Prince Jackson E528714 entity
Predicate mother P120 FINISHED
Object Debbie Rowe 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: Debbie Rowe | Statement: [Prince Jackson, mother, Debbie Rowe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Debbie Rowe
Context triple: [Prince Jackson, mother, Debbie Rowe]
  • A. Debbie Rowe chosen
    Debbie Rowe is an American nurse best known as Michael Jackson’s ex-wife and the mother of two of his children.
  • B. Deedee Rogers
    Deedee Rogers is an individual known primarily through her personal association with Emma Jacklin.
  • C. Sandy Rogers
    Sandy Rogers is one of the adopted children of American singer, actress, and cowgirl icon Dale Evans and her husband Roy Rogers.
  • D. Carol Kaye
    Carol Kaye is a highly influential American session bassist and guitarist, renowned for her prolific work on countless 1960s and 1970s pop, rock, and film soundtrack recordings.
  • E. Dyan Cannon
    Dyan Cannon is an American actress, director, and producer known for her work in film and television since the 1960s, as well as for her high-profile marriage to Cary Grant.
  • 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_69e0c455f3688190810bc96365791b0f completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b5326c8481908a6ab7d2dd961ae2 completed April 22, 2026, 11:46 a.m.
Created at: April 16, 2026, 5:50 p.m.