Triple

T22292523
Position Surface form Disambiguated ID Type / Status
Subject Ashok Saraf E551031 entity
Predicate notableWork P4 FINISHED
Object Karan Arjun E1466591 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: Karan Arjun | Statement: [Ashok Saraf, notableWork, Karan Arjun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Karan Arjun
Context triple: [Ashok Saraf, notableWork, Karan Arjun]
  • A. Karan Arjun chosen
    Karan Arjun is a 1995 Indian Hindi-language action drama film directed by Rakesh Roshan, known for its blend of reincarnation, family revenge, and star performances by Shah Rukh Khan and Salman Khan.
  • B. Karan Kapoor
    Karan Kapoor is an Indian-born former model, photographer, and actor known for his work in 1980s Hindi cinema and British television, as well as for being part of the prominent Kapoor film family.
  • C. Siddharth
    Siddharth is an Indian actor known for his work in Hindi and South Indian cinema, including a prominent role in the film "Rang De Basanti."
  • D. Karanvir Sharma
    Karanvir Sharma is an Indian film and television actor known for his roles in Hindi movies and popular TV dramas.
  • E. Rahul Khanna
    Rahul Khanna is an Indian actor known for his work in Hindi films and television, often recognized for his nuanced performances and understated screen presence.
  • 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_69e11e45fb848190a1b2ae21296e3a5f completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1560d1ec48190ab86f158c94b677b completed April 29, 2026, 12:51 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0abcb1db708190867a631a29583908 completed May 18, 2026, 7:16 a.m.
Created at: April 16, 2026, 8:41 p.m.