Triple

T8667658
Position Surface form Disambiguated ID Type / Status
Subject Subramaniapuram E205715 entity
Predicate producer P490 FINISHED
Object M. Sasikumar E770575 NE FINISHED

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: M. Sasikumar | Statement: [Subramaniapuram, producer, M. Sasikumar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: M. Sasikumar
Context triple: [Subramaniapuram, producer, M. Sasikumar]
  • A. M. Sasikumar chosen
    M. Sasikumar is an Indian filmmaker and actor best known for his critically acclaimed Tamil film "Subramaniapuram," which he directed and starred in.
  • B. K. Balaji
    K. Balaji was an Indian film producer and actor known for his work in Tamil cinema and for producing several successful remakes of Hindi films.
  • C. C. V. Mohan
    C. V. Mohan is an Indian film producer best known as a co-founder of the prominent Telugu film production company Mythri Movie Makers.
  • D. K. K. Venugopal
    K. K. Venugopal is a prominent Indian jurist who served as the Attorney General for India and is renowned for his constitutional law expertise and appearances before the Supreme Court.
  • E. V. T. Vijayan
    V. T. Vijayan is an Indian film editor best known for his acclaimed work in Tamil cinema, including the classic crime drama "Nayakan."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca83516ae88190aefe034b3bc589e3 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc48a34b808190aa9aed9cdb2900e6 completed March 31, 2026, 10:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69cffd5e548c8190898c01f9b8a27175 completed April 3, 2026, 5:48 p.m.
Created at: March 30, 2026, 6:31 p.m.