Triple

T20170819
Position Surface form Disambiguated ID Type / Status
Subject Ashok Kumar E491951 entity
Predicate relative P37 FINISHED
Object Amit Kumar NE NERFINISHED

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: Amit Kumar | Statement: [Ashok Kumar, relative, Amit Kumar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amit Kumar
Context triple: [Ashok Kumar, relative, Amit Kumar]
  • A. Amit Kumar chosen
    Amit Kumar is an Indian playback singer and actor, best known as the son of legendary singer Kishore Kumar and for his work in Hindi cinema music.
  • B. Ajay Kumar
    Ajay Kumar is an Indian screenwriter best known for contributing dialogue to major Telugu-language films, including the epic blockbuster "Baahubali: The Beginning."
  • C. Sumit Kumar
    Sumit Kumar is known primarily as a son of the legendary Indian playback singer and actor Kishore Kumar.
  • D. Ameet Shukla
    Ameet Shukla is a film producer best known for his work on the action thriller movie "Cold Pursuit."
  • E. Anil Kumar
    Anil Kumar is an Indian business leader and academic figure best known for playing a key role in establishing the Indian School of Business as a premier management institution.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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.
Created at: April 11, 2026, 11:35 p.m.