Triple

T21944808
Position Surface form Disambiguated ID Type / Status
Subject Hu Tu Tu E541907 entity
Predicate castMember P1668 FINISHED
Object Suhasini Mulay 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: Suhasini Mulay | Statement: [Hu Tu Tu, castMember, Suhasini Mulay]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Suhasini Mulay
Context triple: [Hu Tu Tu, castMember, Suhasini Mulay]
  • A. Suhasini Mulay chosen
    Suhasini Mulay is an Indian actress and documentary filmmaker known for her work in parallel cinema and acclaimed character roles in Hindi and regional films.
  • B. Uma Maheswari
    Uma Maheswari is a Hindu goddess venerated as the consort of Lord Shiva and a local deity associated with the town of Sirkazhi in Tamil Nadu, India.
  • C. Kalyanee Mulay
    Kalyanee Mulay is an Indian actress known for her work in Marathi and Hindi cinema and theatre, including roles in critically acclaimed independent films.
  • D. Shobha Devi
    Shobha Devi was the wife of legendary Indian film actor Ashok Kumar.
  • E. Leela Naidu
    Leela Naidu was an Indian actress and former Miss India known for her acclaimed but selective film work, including notable roles in both Indian and international cinema.
  • 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_69f1242688988190a7b8f033c49368de completed April 28, 2026, 9:18 p.m.
Created at: April 16, 2026, 7:56 p.m.