Triple

T11643442
Position Surface form Disambiguated ID Type / Status
Subject Marc de La Bruyère E276717 entity
Predicate spouse P13 FINISHED
Object Stacy Schiff E366665 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: Stacy Schiff | Statement: [Marc de La Bruyère, spouse, Stacy Schiff]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stacy Schiff
Context triple: [Marc de La Bruyère, spouse, Stacy Schiff]
  • A. Stacy Schiff
    Stacy Schiff is a Pulitzer Prize–winning American biographer and essayist known for acclaimed works on figures such as Cleopatra, Vera Nabokov, and the Salem witch trials.
  • B. Amanda Foreman
    Amanda Foreman is an American actress best known for her recurring role as Meghan Rotundi on the television series "Felicity."
  • C. Amanda Foreman
    Amanda Foreman is a British-American historian and biographer best known for her acclaimed works on Georgian and Civil War-era history, including the biography of Georgiana, Duchess of Devonshire that inspired the film "The Duchess."
  • D. Stacy Madeleine Schiff chosen
    Stacy Madeleine Schiff is a Pulitzer Prize–winning American author and biographer known for her meticulously researched works on historical figures such as Cleopatra and Vera Nabokov.
  • E. Mildred Wilentz
    Mildred Wilentz was an American editor and publisher known for her influential work in mid-20th-century literary and political publishing circles.
  • 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_69d6aafbb3c081908a9cdb4ecb8d981d completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a2cb4ca88190a9322f08416d3974 completed April 10, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69f019075f4c81908e0cde830231b229 completed April 28, 2026, 2:18 a.m.
Created at: April 8, 2026, 9:39 p.m.