Triple

T11535412
Position Surface form Disambiguated ID Type / Status
Subject Randhir Kapoor E273533 entity
Predicate directorOf P537 FINISHED
Object Dharam Karam E931350 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: Dharam Karam | Statement: [Randhir Kapoor, directorOf, Dharam Karam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dharam Karam
Context triple: [Randhir Kapoor, directorOf, Dharam Karam]
  • A. Dharam Karam chosen
    Dharam Karam is a 1975 Hindi drama film directed by Randhir Kapoor, known for its themes of fate and upbringing and featuring performances by Raj Kapoor, Randhir Kapoor, and Rekha.
  • B. Kallar
    Kallar was a prominent ruler of the Hindu Shahi dynasty, known for leading this early medieval Indian kingdom in the northwestern regions of the subcontinent.
  • C. Dhool
    Dhool is a popular 2003 Tamil action-comedy film starring Vikram, known for its mass appeal, energetic performances, and hit soundtrack.
  • D. Aakrosh
    Aakrosh is a critically acclaimed 1980 Indian Hindi-language crime drama film directed by Govind Nihalani, known for its powerful social commentary and intense performances.
  • E. Bundal Baaz
    Bundal Baaz is a 1976 Hindi fantasy-comedy film starring Shammi Kapoor, known for its lighthearted blend of romance, magic, and humor.
  • 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_69d6aae3fbec8190a14632a5df2538b6 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8839b4bb48190b748ec4119f36c11 completed April 10, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e7fe305c8190bbf981b2c0e63983 completed April 21, 2026, 2:59 a.m.
Created at: April 8, 2026, 9:37 p.m.