Triple

T12349702
Position Surface form Disambiguated ID Type / Status
Subject Marvin Gaye E294449 entity
Predicate associatedAct P37 FINISHED
Object Mary Wells E342076 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: Mary Wells | Statement: [Marvin Gaye, associatedAct, Mary Wells]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Wells
Context triple: [Marvin Gaye, associatedAct, Mary Wells]
  • A. Mary Wells chosen
    Mary Wells was a pioneering American soul and pop singer, often called "The First Lady of Motown" for hits like "My Guy" that helped define the label's early success.
  • B. Mary Lou Adams
    Mary Lou Adams is best known as the former wife of American pop artist James Rosenquist.
  • C. Mary Wills
    Mary Wills was an American costume designer known for her work on major mid-20th-century Hollywood films and for winning an Academy Award for Best Costume Design.
  • D. Lucille Wilson
    Lucille Wilson was the fourth wife of jazz legend Louis Armstrong, known for her long marriage to him and for preserving and promoting his legacy.
  • E. Mary Lou Cook
    Mary Lou Cook was the wife of American character actor Elisha Cook Jr., known for her connection to his long Hollywood career.
  • 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f7cbff08190849cd2aec4ce3243 completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f69b7e7454819099d89db93d0fc1ea completed May 3, 2026, 12:49 a.m.
Created at: April 8, 2026, 9:53 p.m.