Triple

T21944147
Position Surface form Disambiguated ID Type / Status
Subject Hindi Medium E541892 entity
Predicate leadActress P6108 FINISHED
Object Saba Qamar 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: Saba Qamar | Statement: [Hindi Medium, leadActress, Saba Qamar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saba Qamar
Context triple: [Hindi Medium, leadActress, Saba Qamar]
  • A. Saba Qamar chosen
    Saba Qamar is a acclaimed Pakistani actress and television personality known for her versatile performances in film and drama across Pakistan and India.
  • B. Umaima Marvi
    Umaima Marvi is the wife of educator and Khan Academy founder Sal Khan.
  • C. Safia Akhtar
    Safia Akhtar was the mother of renowned Indian lyricist and screenwriter Javed Akhtar and a member of a prominent literary family.
  • D. Zaira Wasim
    Zaira Wasim is an Indian former actress best known for her critically acclaimed debut role in the blockbuster film "Dangal" and her National Film Award–winning performance in "Secret Superstar."
  • E. Ayesha Takia
    Ayesha Takia is an Indian actress best known for her work in Hindi films during the 2000s, including popular roles in movies like "Dor" and "Wanted."
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1242688988190a7b8f033c49368de completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.