Triple

T23224281
Position Surface form Disambiguated ID Type / Status
Subject Bengali popular culture E580976 entity
Predicate hasKeyFigure P810 FINISHED
Object Shabana (actress) 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: Shabana (actress) | Statement: [Bengali popular culture, hasKeyFigure, Shabana (actress)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shabana (actress)
Context triple: [Bengali popular culture, hasKeyFigure, Shabana (actress)]
  • A. Salma Shabana
    Salma Shabana is an Egyptian professional squash player known for competing on the international women’s squash circuit.
  • B. Sakina Ansari
    Sakina Ansari is a daughter of the acclaimed American playwright August Wilson.
  • C. Shabana chosen
    Shabana is a prominent Bangladeshi film actress renowned for her extensive and influential career in Bengali cinema.
  • D. Sakina Jaffrey
    Sakina Jaffrey is an American actress known for her roles in television series such as House of Cards, Timeless, and Billions, as well as numerous film and stage appearances.
  • E. Nadira Babbar
    Nadira Babbar is an Indian theatre director and actress known for her work in Hindi cinema and on stage, including a role in the film "Bride and Prejudice."
  • 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_69e246043c48819089bae72c9a9c306c completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f1922b4a348190ae570a869e30059f completed April 29, 2026, 5:07 a.m.
Created at: April 17, 2026, 4:08 p.m.