Triple

T8110954
Position Surface form Disambiguated ID Type / Status
Subject Moira Kelly E189346 entity
Predicate portrayedCharacter P1668 FINISHED
Object Diana Vreeland E210351 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: Diana Vreeland | Statement: [Moira Kelly, portrayedCharacter, Diana Vreeland]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Vreeland
Context triple: [Moira Kelly, portrayedCharacter, Diana Vreeland]
  • A. Diana Vreeland chosen
    Diana Vreeland was a legendary fashion editor and style icon who shaped 20th-century fashion through her influential work at major magazines and as a consultant to the Metropolitan Museum of Art’s Costume Institute.
  • B. Annette de la Renta
    Annette de la Renta is a New York–based socialite and philanthropist known for her prominent role in high society and as the widow of fashion designer Oscar de la Renta.
  • C. Nora Wintour
    Nora Wintour is a British trade union and labor rights activist known for her work with international labor organizations and campaigns to improve workers’ conditions worldwide.
  • D. Anna Wintour
    Anna Wintour is the influential longtime editor-in-chief of Vogue and a powerful figure in the global fashion industry.
  • E. Lillian Goldman
    Lillian Goldman was a philanthropist and major benefactor of legal education and libraries, notably supporting Yale Law School.
  • 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_69ca82b9d5848190a24672775d5c5011 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb42fcfb9c81908496f9a7e30d0d8a completed March 31, 2026, 3:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc942a9af881908b7ddc724755893e completed April 1, 2026, 3:42 a.m.
Created at: March 30, 2026, 5:32 p.m.