Triple

T18922246
Position Surface form Disambiguated ID Type / Status
Subject Condor E462885 entity
Predicate starring P1507 FINISHED
Object Mira Sorvino 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: Mira Sorvino | Statement: [Condor, starring, Mira Sorvino]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mira Sorvino
Context triple: [Condor, starring, Mira Sorvino]
  • A. Mira Sorvino chosen
    Mira Sorvino is an American actress and Academy Award winner known for her versatile performances in film and television.
  • B. Marisa Tomei
    Marisa Tomei is an Academy Award–winning American actress known for her versatile film and television roles, including portraying Aunt May in the Marvel Cinematic Universe.
  • C. Annabella Sciorra
    Annabella Sciorra is an American actress known for her work in film and television, including acclaimed roles in movies like "Jungle Fever" and the TV series "The Sopranos."
  • D. Lorraine Bracco
    Lorraine Bracco is an American actress best known for her roles in the film "Goodfellas" and the television series "The Sopranos."
  • E. Téa Leoni
    Téa Leoni is an American actress and producer best known for her leading roles in film and television, including the political drama series "Madam Secretary."
  • 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_69d8dcfdbbb881909964fa5a75bd0b48 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c9b4822c8190a0aeceb4499e775e completed April 20, 2026, 6:37 a.m.
Created at: April 10, 2026, 11:59 a.m.