Triple

T8154157
Position Surface form Disambiguated ID Type / Status
Subject Sanjeev Bhaskar E190402 entity
Predicate coStarredWith P14987 FINISHED
Object Meera Syal E191276 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: Meera Syal | Statement: [Sanjeev Bhaskar, coStarredWith, Meera Syal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Meera Syal
Context triple: [Sanjeev Bhaskar, coStarredWith, Meera Syal]
  • A. Meera Syal chosen
    Meera Syal is a British comedian, writer, playwright, and actress known for her work on "Goodness Gracious Me," "The Kumars at No. 42," and numerous stage and screen roles.
  • B. Reema Lagoo
    Reema Lagoo was a prominent Indian film, television, and theatre actress best known for playing iconic motherly roles in Hindi and Marathi cinema.
  • C. Reeta Chakrabarti
    Reeta Chakrabarti is a British journalist, newsreader, and correspondent best known for her work with BBC News.
  • D. Salma Lakhani
    Salma Lakhani is a Canadian businesswoman and philanthropist who became the first Muslim and first South Asian to serve as a lieutenant governor in Canada.
  • E. Persis Khambatta
    Persis Khambatta was an Indian model and actress best known internationally for her role as Lieutenant Ilia in "Star Trek: The Motion Picture."
  • 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_69ca82bfeb6481909d07b91b5cf69f59 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb44d566b08190a6bb672f9c368806 completed March 31, 2026, 3:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69cced43a5448190b2600cbdbabf9d31 completed April 1, 2026, 10:02 a.m.
Created at: March 30, 2026, 5:37 p.m.