Triple

T21202661
Position Surface form Disambiguated ID Type / Status
Subject Amrita Pritam E522495 entity
Predicate familyName P18 FINISHED
Object Pritam 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: Pritam | Statement: [Amrita Pritam, familyName, Pritam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pritam
Context triple: [Amrita Pritam, familyName, Pritam]
  • A. Pritam chosen
    Pritam is the surname of Amrita Pritam, the renowned Indian Punjabi poet and novelist.
  • B. Pritam Chakraborty
    Pritam Chakraborty is a prominent Indian film composer and music director known for his hit soundtracks in contemporary Bollywood cinema.
  • C. Pritam Singh
    Pritam Singh was the husband of renowned Punjabi writer and poet Amrita Pritam, known primarily in relation to her life and literary legacy.
  • D. Pritam Singh
    Pritam Singh is a Singaporean politician who serves as the Secretary-General of the Workers’ Party and Leader of the Opposition in Singapore’s Parliament.
  • E. Pritam Das
    Pritam Das is an Indian cricketer known for representing Assam in domestic cricket competitions.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e73432a2b88190a89e636626d40c9b completed April 21, 2026, 8:24 a.m.
Created at: April 16, 2026, 3:19 p.m.