Triple

T22403691
Position Surface form Disambiguated ID Type / Status
Subject Nagraj Manjule E553825 entity
Predicate directorOf P537 FINISHED
Object Jhund 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: Jhund | Statement: [Nagraj Manjule, directorOf, Jhund]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jhund
Context triple: [Nagraj Manjule, directorOf, Jhund]
  • A. Jhund chosen
    Jhund is a 2019 Indian sports drama film directed by Nagraj Manjule that tells the story of a football team formed from underprivileged slum children in Nagpur.
  • B. Jhalmuri
    Jhalmuri is a notable literary work by Bangladeshi poet Al Mahmud, recognized for its contribution to modern Bengali literature.
  • C. Dhumakot
    Dhumakot is a small town in the hilly region of Uttarakhand, India, known for its rural setting and scenic surroundings.
  • D. Dhum Dhadaka
    Dhum Dhadaka is a popular Marathi comedy film best known for its humorous storyline and memorable performance by Ashok Saraf.
  • E. Taymuri
    Taymuri are a sub-group of the Aimaq people, traditionally semi-nomadic pastoralists living mainly in western and central Afghanistan.
  • 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_69e11e4da7048190b4387d422a9a0de5 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f158b6762c8190991fc14c5ca8e609 completed April 29, 2026, 1:02 a.m.
Created at: April 16, 2026, 8:46 p.m.