Triple

T22273844
Position Surface form Disambiguated ID Type / Status
Subject Sholay E550550 entity
Predicate screenwriter P2831 FINISHED
Object Salim Khan 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: Salim Khan | Statement: [Sholay, screenwriter, Salim Khan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salim Khan
Context triple: [Sholay, screenwriter, Salim Khan]
  • A. Salim Khan chosen
    Salim Khan is a prominent Indian screenwriter and actor, best known as one half of the legendary Bollywood writing duo Salim–Javed that revolutionized Hindi cinema in the 1970s and 1980s.
  • B. Alim Khan
    Alim Khan was a prominent early 19th-century khan of the Kokand Khanate in Central Asia, known for expanding its territory and consolidating its political power.
  • C. Amjad Khan
    Amjad Khan was a renowned Indian film actor best known for his iconic villainous roles in Hindi cinema, particularly as Gabbar Singh in "Sholay."
  • D. Feroz Abbas Khan
    Feroz Abbas Khan is an Indian theatre and film director known for his acclaimed stage productions and for adapting powerful historical and literary works to screen and stage.
  • E. Farooq Shaikh
    Farooq Shaikh was a renowned Indian film and television actor best known for his nuanced performances in parallel cinema and middle-class comedies from the late 1970s through the 1990s.
  • 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.