Triple

T18704085
Position Surface form Disambiguated ID Type / Status
Subject Leverage team E457326 entity
Predicate hasMember P10 FINISHED
Object Breanna Casey 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: Breanna Casey | Statement: [Leverage team, hasMember, Breanna Casey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Breanna Casey
Context triple: [Leverage team, hasMember, Breanna Casey]
  • A. Brianna Casey chosen
    Brianna Casey is a professional associated with the Leverage team, likely contributing specialized skills or expertise within that organization.
  • B. Breanna Barnes
    Breanna Barnes is the central protagonist of the work "One on One," around whom the main narrative and character development revolve.
  • C. Brianna Brown
    Brianna Brown is an American actress known for her work in television and film, including prominent roles in various drama and thriller series.
  • D. Brooklyn Decker
    Brooklyn Decker is an American model and actress known for her Sports Illustrated Swimsuit Issue appearances and roles in films and television comedies.
  • E. Briana Evigan
    Briana Evigan is an American actress and dancer best known for her breakout lead role in the dance film "Step Up 2: The Streets" and subsequent work in horror and thriller movies.
  • 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_69d8d392aad081909fe31aa03e6e97d1 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5671597ac819093dbb53553130f1e completed April 19, 2026, 11:36 p.m.
Created at: April 10, 2026, 11:49 a.m.