Triple

T22433223
Position Surface form Disambiguated ID Type / Status
Subject Lootera E554548 entity
Predicate producer P490 FINISHED
Object Ekta Kapoor 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: Ekta Kapoor | Statement: [Lootera, producer, Ekta Kapoor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ekta Kapoor
Context triple: [Lootera, producer, Ekta Kapoor]
  • A. Ekta Kapoor chosen
    Ekta Kapoor is a prominent Indian television and film producer known for revolutionizing Hindi soap operas and co-founding Balaji Telefilms.
  • B. Rhea Kapoor
    Rhea Kapoor is an Indian film producer and fashion stylist known for producing Bollywood films like "Aisha" and "Veere Di Wedding" and for her work in celebrity styling.
  • C. Khushi Kapoor
    Khushi Kapoor is an Indian actress and model, best known as the younger daughter of legendary Bollywood star Sridevi and film producer Boney Kapoor.
  • D. Parineeti Chopra
    Parineeti Chopra is an Indian film actress known for her work in Hindi cinema, particularly in romantic comedies and dramas.
  • E. Sanya Malhotra
    Sanya Malhotra is an Indian actress known for her acclaimed debut in the film "Dangal" and subsequent roles in Hindi cinema.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a3320448190ae3931062599116e completed April 29, 2026, 1:09 a.m.
Created at: April 16, 2026, 8:47 p.m.