Triple

T17573331
Position Surface form Disambiguated ID Type / Status
Subject Odette Yustman E427994 entity
Predicate name P16 FINISHED
Object Odette Yustman 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: Odette Yustman | Statement: [Odette Yustman, name, Odette Yustman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Odette Yustman
Context triple: [Odette Yustman, name, Odette Yustman]
  • A. Odette Yustman chosen
    Odette Yustman is an American actress known for her roles in films such as Cloverfield and The Unborn, as well as various television series.
  • B. Etti Kirshner
    Etti Kirshner is a relative of Canadian actress Mia Kirshner, known for her work in film and television.
  • C. Lila Schwarzenberg
    Lila Schwarzenberg is an Austrian journalist, philanthropist, and former Czech countess known for her cultural and charitable work in Europe.
  • D. Aida Braverman
    Aida Braverman is a fictional child character from the television series "Parenthood," known as the daughter of Crosby Braverman and Jasmine Trussell.
  • E. Elsa Zylberstein
    Elsa Zylberstein is a French actress known for her nuanced performances in film and television, often in emotionally complex dramatic roles.
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e459330c788190907a02fc98e0e24b completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.