Triple

T22075513
Position Surface form Disambiguated ID Type / Status
Subject Mahal (1949 film) E545511 entity
Predicate director P255 FINISHED
Object Kamal Amrohi 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: Kamal Amrohi | Statement: [Mahal (1949 film), director, Kamal Amrohi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kamal Amrohi
Context triple: [Mahal (1949 film), director, Kamal Amrohi]
  • A. Kamal Amrohi chosen
    Kamal Amrohi was a renowned Indian film director, screenwriter, and producer best known for classic Hindi cinema works such as "Mahal" and "Pakeezah."
  • B. M.S. Sathyu
    M.S. Sathyu is an acclaimed Indian film director best known for his socially conscious and politically charged works, including the landmark film "Garm Hava," which helped define the parallel cinema movement.
  • C. Hrishikesh Mukherjee
    Hrishikesh Mukherjee was a celebrated Indian film director and editor, best known for his warm, middle-class family dramas and comedies in Hindi cinema from the 1960s to the 1980s.
  • D. Hansal Mehta
    Hansal Mehta is an Indian filmmaker and director known for critically acclaimed films and series such as "Shahid," "Aligarh," and "Scam 1992."
  • E. Govind Nihalani
    Govind Nihalani is an acclaimed Indian cinematographer and filmmaker known for his work in parallel cinema and socially conscious films.
  • 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_69e11e344dfc81909b1d88a7221329c7 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128b1904881909a1769ce8be39e05 completed April 28, 2026, 9:37 p.m.
Created at: April 16, 2026, 8:28 p.m.