Triple

T22273868
Position Surface form Disambiguated ID Type / Status
Subject Sholay E550550 entity
Predicate castMember P1668 FINISHED
Object Sanjeev Kumar 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: Sanjeev Kumar | Statement: [Sholay, castMember, Sanjeev Kumar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanjeev Kumar
Context triple: [Sholay, castMember, Sanjeev Kumar]
  • A. Sanjeev Kumar chosen
    Sanjeev Kumar was a highly acclaimed Indian film actor known for his versatile performances in both mainstream and parallel cinema during the 1960s and 1970s.
  • B. Dilip Kumar
    Dilip Kumar was a legendary Indian film actor, celebrated as the "Tragedy King" of Hindi cinema and renowned for his intense, nuanced performances in classic Bollywood films.
  • C. Shashi Kapoor
    Shashi Kapoor was a prominent Indian film actor and producer, known for his work in Hindi cinema and international films, and as a member of the influential Kapoor family.
  • D. Tarun Dutt
    Tarun Dutt was the son of legendary Indian filmmaker and actor Guru Dutt, known primarily for his connection to this iconic figure in Indian cinema.
  • E. Dharmendra
    Dharmendra is a legendary Indian film actor, often called the "He-Man" of Bollywood, known for his prolific work in Hindi cinema since the 1960s.
  • 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_69e11e43d8208190aff4f9cf7f2c2a8a completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f14ea547e4819098baf88f3c605242 completed April 29, 2026, 12:19 a.m.
Created at: April 16, 2026, 8:40 p.m.