Triple

T5462301
Position Surface form Disambiguated ID Type / Status
Subject Ardh Satya E122620 entity
Predicate starring P1507 FINISHED
Object Om Puri E126666 NE FINISHED

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: Om Puri | Statement: [Ardh Satya, starring, Om Puri]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Om Puri
Context triple: [Ardh Satya, starring, Om Puri]
  • A. Om Puri chosen
    Om Puri was a renowned Indian actor celebrated for his powerful performances in both parallel and mainstream cinema, as well as notable roles in international films.
  • B. Balu Mahendra
    Balu Mahendra was an acclaimed Indian filmmaker and cinematographer known for his visually poetic, character-driven films primarily in Tamil cinema.
  • C. Bhanu Athaiya
    Bhanu Athaiya was an acclaimed Indian costume designer and the first Indian to win an Academy Award, renowned for her work in both Indian and international cinema.
  • D. Bimal Parekh
    Bimal Parekh is an Indian businessman and co-owner of the Indian Super League football club Mumbai City FC.
  • E. Tapan Sinha
    Tapan Sinha was a renowned Indian film director celebrated for his socially conscious and critically acclaimed works in Bengali cinema.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd4643f16081908d7f29e08096115a completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd92033dd08190a90bcae6b9f149d3 completed March 20, 2026, 6:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf414ebd288190ae90593232ff2db9 completed March 22, 2026, 1:09 a.m.
Created at: March 20, 2026, 2:08 p.m.