Triple

T23439417
Position Surface form Disambiguated ID Type / Status
Subject Anushka Sharma E565353 entity
Predicate notableWork P4 FINISHED
Object Sanju 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: Sanju | Statement: [Anushka Sharma, notableWork, Sanju]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sanju
Context triple: [Anushka Sharma, notableWork, Sanju]
  • A. Sanju chosen
    Sanju is a 2018 Hindi biographical drama film that chronicles the tumultuous life of Bollywood actor Sanjay Dutt, directed by Rajkumar Hirani and starring Ranbir Kapoor in the title role.
  • B. Jawan
    Jawan is a 2023 Indian action thriller film starring Shah Rukh Khan, known for its high-octane action, social themes, and massive box-office success.
  • C. Jawan
    Jawan is an alternative name for the Jawoyn, an Aboriginal Australian people from the Northern Territory known for their rich cultural heritage and connection to the Nitmiluk (Katherine Gorge) region.
  • D. Jawan
    Jawan is a small town in the Aligarh district of Uttar Pradesh, India, known primarily as a local agricultural and market center.
  • E. Kaalpurush
    Kaalpurush is an acclaimed Bengali film by director Buddhadeb Dasgupta that explores memory, time, and human relationships through a poetic, surreal narrative.
  • 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_69e24584f9488190bb32730bd2ce023e completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a5de713c8190b35bfa66dddbd5af completed April 29, 2026, 6:31 a.m.
Created at: April 17, 2026, 5:50 p.m.