Triple

T20170768
Position Surface form Disambiguated ID Type / Status
Subject Kishore Kumar E491950 entity
Predicate sibling P363 FINISHED
Object Anup Kumar
Anup Kumar was an Indian actor and comedian best known for his work in Hindi cinema, particularly in supporting and character roles.
E1416009 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: Anup Kumar | Statement: [Kishore Kumar, sibling, Anup Kumar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anup Kumar
Context triple: [Kishore Kumar, sibling, Anup Kumar]
  • A. Anup Kumar
    Anup Kumar is an Indian kabaddi player renowned for his leadership of the national team and his success in the Pro Kabaddi League.
  • B. Ravi Nandan
    Ravi Nandan is a television and film producer known for his executive production work on comedy series such as "Playing House."
  • C. Himanshu Rai
    Himanshu Rai was a prominent Indian actor and pioneering film producer-director, best known for co-founding Bombay Talkies and helping shape early Indian cinema.
  • D. Arun Dutt
    Arun Dutt is an Indian film personality best known as the son of legendary filmmaker and actor Guru Dutt.
  • E. Manoj Tiwary
    Manoj Tiwary is an Indian cricketer known primarily as a prolific middle-order batsman in domestic cricket and a former international player for India.
  • 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: Anup Kumar
Triple: [Kishore Kumar, sibling, Anup Kumar]
Generated description
Anup Kumar was an Indian actor and comedian best known for his work in Hindi cinema, particularly in supporting and character roles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anup Kumar
Target entity description: Anup Kumar was an Indian actor and comedian best known for his work in Hindi cinema, particularly in supporting and character roles.
  • A. Anup Kumar
    Anup Kumar is an Indian kabaddi player renowned for his leadership of the national team and his success in the Pro Kabaddi League.
  • B. Ravi Nandan
    Ravi Nandan is a television and film producer known for his executive production work on comedy series such as "Playing House."
  • C. Himanshu Rai
    Himanshu Rai was a prominent Indian actor and pioneering film producer-director, best known for co-founding Bombay Talkies and helping shape early Indian cinema.
  • D. Arun Dutt
    Arun Dutt is an Indian film personality best known as the son of legendary filmmaker and actor Guru Dutt.
  • E. Manoj Tiwary
    Manoj Tiwary is an Indian cricketer known primarily as a prolific middle-order batsman in domestic cricket and a former international player for India.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66847ed9481908e6b23b399fa7005 completed April 20, 2026, 5:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a083c74d970819085ae9ad5e0aaaf8f completed May 16, 2026, 9:44 a.m.
NEDg Description generation batch_6a083d5360cc8190b5c3e2df33b6ef2b completed May 16, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_6a083dce8b8881908c26f6fe5ba8a8cc completed May 16, 2026, 9:50 a.m.
Created at: April 11, 2026, 11:35 p.m.