Triple

T16792006
Position Surface form Disambiguated ID Type / Status
Subject Rajat Kapoor E408131 entity
Predicate participatedIn P149 FINISHED
Object Kadakh (as actor)
Kadakh is a Hindi-language dark comedy thriller film featuring Rajat Kapoor in an acting role.
 E1233647 NE FINISHED

How this triple was built (4 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: Kadakh (as actor) | Statement: [Rajat Kapoor, participatedIn, Kadakh (as actor)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kadakh (as actor)
Context triple: [Rajat Kapoor, participatedIn, Kadakh (as actor)]
  • A. Karan
    Karan is the given first name of Lord Bilimoria, a prominent British-Indian entrepreneur and life peer.
  • B. Kaththi
    Kaththi is a 2014 Tamil action-drama film directed by A.R. Murugadoss, starring Vijay in a dual role and focusing on social issues like farmer exploitation and corporate greed.
  • C. Zarganar
    Zarganar is a prominent Burmese comedian, actor, and dissident known for his sharp political satire and repeated imprisonments under Myanmar’s military regimes.
  • D. Dastagir
    Dastagir is a residential neighborhood located within the Federal B Area of Karachi, Pakistan.
  • E. Shahid
    "Shahid" is a critically acclaimed 2013 Indian biographical drama film starring Rajkummar Rao as human rights lawyer Shahid Azmi, charting his journey from wrongful imprisonment to his work defending those accused under anti-terror laws.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kadakh (as actor)
Triple: [Rajat Kapoor, participatedIn, Kadakh (as actor)]
Generated description
Kadakh is a Hindi-language dark comedy thriller film featuring Rajat Kapoor in an acting role.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kadakh (as actor)
Target entity description: Kadakh is a Hindi-language dark comedy thriller film featuring Rajat Kapoor in an acting role.
  • A. Karan
    Karan is the given first name of Lord Bilimoria, a prominent British-Indian entrepreneur and life peer.
  • B. Kaththi
    Kaththi is a 2014 Tamil action-drama film directed by A.R. Murugadoss, starring Vijay in a dual role and focusing on social issues like farmer exploitation and corporate greed.
  • C. Zarganar
    Zarganar is a prominent Burmese comedian, actor, and dissident known for his sharp political satire and repeated imprisonments under Myanmar’s military regimes.
  • D. Dastagir
    Dastagir is a residential neighborhood located within the Federal B Area of Karachi, Pakistan.
  • E. Shahid
    "Shahid" is a critically acclaimed 2013 Indian biographical drama film starring Rajkummar Rao as human rights lawyer Shahid Azmi, charting his journey from wrongful imprisonment to his work defending those accused under anti-terror laws.
  • F. None of above. chosen

Provenance (5 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_69d8839270588190886720d9519bbf8f completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3b2a6c9888190b3f8f625b299574d completed April 18, 2026, 4:34 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00ab0c39108190a332fdc78c053628 completed May 10, 2026, 3:58 p.m.
NEDg Description generation batch_6a00ac621b3881908887b640bf3e3fce completed May 10, 2026, 4:03 p.m.
NED2 Entity disambiguation (via description) batch_6a00acc3a9dc819087e07e539760bf34 completed May 10, 2026, 4:05 p.m.
Created at: April 10, 2026, 5:22 a.m.