Triple

T23263930
Position Surface form Disambiguated ID Type / Status
Subject Troy Donahue E582092 entity
Predicate notableWork P4 FINISHED
Object Parrish 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: Parrish | Statement: [Troy Donahue, notableWork, Parrish]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Parrish
Context triple: [Troy Donahue, notableWork, Parrish]
  • A. Parrish
    Parrish is the surname of Kehlani, an American R&B singer, songwriter, and dancer known for her emotionally candid music.
  • B. Parrish chosen
    Parrish is a 1961 American drama film, based on a novel by Mildred Savage, about a young man navigating love and ambition on Connecticut tobacco farms.
  • C. Parrtown
    Parrtown was the original name of the Loyalist settlement that later became the city of Saint John in New Brunswick, Canada.
  • D. Sharswood
    Sharswood is a residential neighborhood in North Philadelphia known for its ongoing redevelopment and proximity to areas like Brewerytown and Girard College.
  • E. Parkside
    Parkside is a primarily residential neighborhood on the western side of San Francisco, known for its quiet streets, proximity to the ocean, and access to public transit.
  • 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_69e246079f58819085eaa9c260906880 completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f194cb76c48190869915cd93b44fcc completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:11 p.m.