Triple

T22102751
Position Surface form Disambiguated ID Type / Status
Subject Saaransh E546210 entity
Predicate starring P1507 FINISHED
Object Soni Razdan 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: Soni Razdan | Statement: [Saaransh, starring, Soni Razdan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soni Razdan
Context triple: [Saaransh, starring, Soni Razdan]
  • A. Soni Razdan chosen
    Soni Razdan is a British-born Indian actress and filmmaker known for her work in Hindi cinema and television, as well as for being the mother of actress Alia Bhatt.
  • B. 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."
  • C. Anu Khosla
    Anu Khosla is one of the children of Indian-American billionaire venture capitalist and Sun Microsystems co-founder Vinod Khosla.
  • D. Poonam Sinha
    Poonam Sinha is an Indian actress and film producer known for her supporting roles in Hindi cinema and as the wife of veteran actor Shatrughan Sinha.
  • E. Dina Pathak
    Dina Pathak was a renowned Indian actress and theatre activist known for her powerful character roles in Hindi and Gujarati cinema and stage.
  • 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_69e11e378dc08190896d6a51597afd5a completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f129175a7881909549883f23c53dca completed April 28, 2026, 9:39 p.m.
Created at: April 16, 2026, 8:30 p.m.