Triple

T22403709
Position Surface form Disambiguated ID Type / Status
Subject Mahesh Manjrekar E553826 entity
Predicate name P16 FINISHED
Object Mahesh Manjrekar 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: Mahesh Manjrekar | Statement: [Mahesh Manjrekar, name, Mahesh Manjrekar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mahesh Manjrekar
Context triple: [Mahesh Manjrekar, name, Mahesh Manjrekar]
  • A. Mahesh Manjrekar chosen
    Mahesh Manjrekar is an Indian filmmaker and actor known for his influential work in Marathi and Hindi cinema, including directing acclaimed films like "Vaastav."
  • B. Kamal Shirwadkar
    Kamal Shirwadkar was the wife of renowned Marathi poet and writer Vishnu Vaman Shirwadkar, popularly known as Kusumagraj.
  • C. Dilip Mehta
    Dilip Mehta is an Indian-born photojournalist and filmmaker known for his documentary and feature film work, often intersecting with the socially conscious cinema of his sister, director Deepa Mehta.
  • D. Roopesh Parekh
    Roopesh Parekh is a television and film producer known for his work on the adaptation of Agatha Christie's "Ordeal by Innocence."
  • E. Vikramaditya Motwane
    Vikramaditya Motwane is an Indian filmmaker and screenwriter known for directing acclaimed films like "Udaan," "Lootera," and the Netflix series "Sacred Games."
  • 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.