Triple

T19948645
Position Surface form Disambiguated ID Type / Status
Subject Sabrina (1995 film) E479494 entity
Predicate starring P1507 FINISHED
Object Nancy Marchand 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: Nancy Marchand | Statement: [Sabrina (1995 film), starring, Nancy Marchand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nancy Marchand
Context triple: [Sabrina (1995 film), starring, Nancy Marchand]
  • A. Nancy Marchand chosen
    Nancy Marchand was an acclaimed American actress best known for her roles on the television series "Lou Grant" and "The Sopranos."
  • B. Christiane Legrand
    Christiane Legrand was a French jazz and classical singer best known as the original lead soprano of The Swingle Singers and for her extensive work on film soundtracks.
  • C. Denise Dion
    Denise Dion is a person notable for sharing the surname associated with the Dion family name.
  • D. Nancy Dubuc
    Nancy Dubuc is an American media executive and producer best known for leading networks like A&E and Vice Media and overseeing hit nonfiction and scripted programming.
  • E. Patti D'Arbanville
    Patti D'Arbanville is an American actress and former model known for her work in film and television since the 1970s, including notable roles in both independent and mainstream productions.
  • 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_69d8e522a17c819095165d4d24939fd8 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65a69ae388190918e862012f9fe39 completed April 20, 2026, 4:55 p.m.
Created at: April 10, 2026, 1:54 p.m.