Triple

T19273977
Position Surface form Disambiguated ID Type / Status
Subject Bharat Ek Khoj E481997 entity
Predicate portrayedBy P1507 FINISHED
Object Roshan Seth 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: Roshan Seth | Statement: [Bharat Ek Khoj, portrayedBy, Roshan Seth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roshan Seth
Context triple: [Bharat Ek Khoj, portrayedBy, Roshan Seth]
  • A. Roshan Seth chosen
    Roshan Seth is an Indian-born British actor known for his character roles in films such as "Gandhi," "Indiana Jones and the Temple of Doom," and numerous British and international productions.
  • B. Dhanraj Pillay
    Dhanraj Pillay is a legendary Indian field hockey forward renowned for his speed, skill, and long international career, including multiple Olympic and World Cup appearances.
  • C. Roshan Sethi
    Roshan Sethi is a physician-turned-screenwriter and television producer best known for co-creating the medical drama series "The Resident."
  • D. Ashok Saraf
    Ashok Saraf is a veteran Indian actor and comedian best known for his prolific work in Marathi films and theatre, as well as memorable roles in Hindi cinema and television.
  • E. Vanraj Bhatia
    Vanraj Bhatia was an acclaimed Indian composer known for his pioneering work in parallel cinema and television, blending Western classical techniques with Indian musical traditions.
  • 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_69d8e8ce54cc8190998418ff1f66ef28 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fbba7758819081c1c78667c59c5e completed April 20, 2026, 10:11 a.m.
Created at: April 10, 2026, 1:29 p.m.