Triple

T17751006
Position Surface form Disambiguated ID Type / Status
Subject Mamata Banerjee E443110 entity
Predicate givenName P17 FINISHED
Object Mamata 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: Mamata | Statement: [Mamata Banerjee, givenName, Mamata]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mamata
Context triple: [Mamata Banerjee, givenName, Mamata]
  • A. Pramila
    Pramila is a prominent female warrior character in the Bengali epic poem "Meghnad Badh Kavya," known for her valor and tragic role in the retelling of the Ramayana.
  • B. Shyamala
    Shyamala is an Indian-origin female given name commonly used in South Asia.
  • C. Vasusena
    Vasusena is the original birth name of Karna, a central warrior figure in the Indian epic Mahabharata.
  • D. Mamta chosen
    Mamta is a classic 1966 Hindi drama film starring Suchitra Sen, known for its emotional story of sacrifice and maternal love.
  • E. Mahāmati
    Mahāmati is a bodhisattva figure in Mahāyāna Buddhism known for his profound questions and role in eliciting the Buddha’s teachings on mind-only doctrine and enlightenment.
  • 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_69d8b9ed3a2081909b2ec0d4dd2f4c37 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841a401c8190ae1dc0ed7ae4cc26 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.