Triple

T21943831
Position Surface form Disambiguated ID Type / Status
Subject Sahabzade Irfan Ali Khan E541886 entity
Predicate spouse P13 FINISHED
Object Sutapa Sikdar 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: Sutapa Sikdar | Statement: [Sahabzade Irfan Ali Khan, spouse, Sutapa Sikdar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sutapa Sikdar
Context triple: [Sahabzade Irfan Ali Khan, spouse, Sutapa Sikdar]
  • A. Sutapa Sikdar chosen
    Sutapa Sikdar is an Indian dialogue and screenplay writer best known as the wife of acclaimed actor Irrfan Khan.
  • B. Sutapa Basu
    Sutapa Basu is an Indian author and poet known for her historical fiction and contemporary novels.
  • C. Sutapa Dasgupta
    Sutapa Dasgupta is known as the wife of acclaimed Indian poet and National Award–winning filmmaker Buddhadeb Dasgupta.
  • D. Supriya Dasgupta
    Supriya Dasgupta is the daughter of acclaimed Indian filmmaker and actress Aparna Sen.
  • E. Anindita Basu
    Anindita Basu is an Indian technical writer and author known for her work in documentation and contributions to open knowledge resources.
  • 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_69e0c47e2e5c81909a7f74ce3de50911 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1242515ec8190b015bf8c7b13be85 completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.