Triple

T20297794
Position Surface form Disambiguated ID Type / Status
Subject A United Kingdom E505397 entity
Predicate producer P490 FINISHED
Object Brunson Green 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: Brunson Green | Statement: [A United Kingdom, producer, Brunson Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brunson Green
Context triple: [A United Kingdom, producer, Brunson Green]
  • A. Brunson Green chosen
    Brunson Green is an American film producer best known for his work on the Academy Award–winning drama "The Help."
  • B. Dupree Park
    Dupree Park is a public recreational park in Woodstock, Georgia, featuring outdoor amenities such as trails, sports facilities, and green space for community activities.
  • C. Marlon G. Priest Park
    Marlon G. Priest Park is a public recreational park located in Shelby, North Carolina.
  • D. Winson Green
    Winson Green is an inner-city area of Birmingham, England, known for its diverse community and the HM Prison Birmingham located there.
  • E. Marcus Garvey Park
    Marcus Garvey Park is a historic public park in Harlem, New York City, known for its cultural significance, community events, and prominent fire watchtower.
  • 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_69e0b4b8ab648190906e18538c250148 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e677095fb481909806214da4002b59 completed April 20, 2026, 6:57 p.m.
Created at: April 16, 2026, 11:16 a.m.