Triple

T12669591
Position Surface form Disambiguated ID Type / Status
Subject David Heitner E302639 entity
Predicate workedOn P3 FINISHED
Object Sarafina! E62321 NE FINISHED

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: Sarafina! | Statement: [David Heitner, workedOn, Sarafina!]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarafina!
Context triple: [David Heitner, workedOn, Sarafina!]
  • A. Sarafina! chosen
    Sarafina! is a 1992 South African musical drama film about a young girl’s coming-of-age during the Soweto uprising against apartheid.
  • B. L’Africaine
    L’Africaine is a grand opera by Giacomo Meyerbeer, renowned for its exotic setting, complex vocal writing, and significant place in 19th-century French opera repertoire.
  • C. A Negra
    A Negra is a seminal modernist painting by Brazilian artist Tarsila do Amaral that explores Afro-Brazilian identity through bold forms and vibrant colors.
  • D. Road to Zanzibar
    Road to Zanzibar is a 1941 musical comedy film starring Bing Crosby and Bob Hope, known as one of the early entries in their popular "Road to..." film series.
  • E. Devil on the Cross
    Devil on the Cross is a politically charged novel by Kenyan writer Ngũgĩ wa Thiong’o that critiques neocolonialism and corruption in post-independence Kenya.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96183a6048190b2ef219eb9d20aa4 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f68ead66bc819099c8d274d69a2022 completed May 2, 2026, 11:54 p.m.
Created at: April 9, 2026, 5:20 p.m.