Triple

T9392298
Position Surface form Disambiguated ID Type / Status
Subject Robert Taylor E226052 entity
Predicate workedWith P398 FINISHED
Object Vivien Leigh E34677 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: Vivien Leigh | Statement: [Robert Taylor, workedWith, Vivien Leigh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vivien Leigh
Context triple: [Robert Taylor, workedWith, Vivien Leigh]
  • A. Vivien Leigh chosen
    Vivien Leigh was a British actress best known for her Academy Award–winning performances as Scarlett O’Hara in "Gone with the Wind" and Blanche DuBois in "A Streetcar Named Desire."
  • B. Anna Maria Dandridge
    Anna Maria Dandridge was a colonial Virginian woman from the prominent Dandridge family, known primarily as a relative of Martha Dandridge Custis Washington, the future First Lady of the United States.
  • C. Suellen O'Hara
    Suellen O'Hara is Scarlett O'Hara’s vain and self-interested younger sister in Margaret Mitchell’s novel "Gone with the Wind."
  • D. Vivian Dandridge
    Vivian Dandridge was an American singer and actress, best known as a member of the Dandridge Sisters vocal group and for her work in early Hollywood entertainment.
  • E. Bette Davis
    Bette Davis was an iconic American film actress renowned for her intense, uncompromising performances and pioneering portrayals of complex, strong-willed women on screen.
  • 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_69ca842f7e3481908bf5bcf52e032dbd completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd510eae0c8190b7c4ab487a366bb3 completed April 1, 2026, 5:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1010169d88190a7267615a9196d4b completed April 4, 2026, 12:16 p.m.
Created at: March 30, 2026, 7:45 p.m.