Triple

T21109628
Position Surface form Disambiguated ID Type / Status
Subject Dadasaheb Phalke E520138 entity
Predicate directed P7373 FINISHED
Object Mohini Bhasmasur E470376 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: Mohini Bhasmasur | Statement: [Dadasaheb Phalke, directed, Mohini Bhasmasur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mohini Bhasmasur
Context triple: [Dadasaheb Phalke, directed, Mohini Bhasmasur]
  • A. Chandramukhi
    Chandramukhi is a courtesan and one of the central tragic figures in Sarat Chandra Chattopadhyay’s novel "Devdas," known for her deep, unrequited love and devotion to the protagonist.
  • B. Chandramukhi
    Chandramukhi is a hugely popular 2005 Tamil horror-comedy film that became one of Rajinikanth’s most successful and influential movies.
  • C. Badinî
    Badinî is a Northern Kurdish dialect spoken primarily in parts of Turkey, Iraq, and Syria.
  • D. Mohini chosen
    Mohini is the enchanting female avatar of the Hindu god Vishnu, famed for her role in various myths where she uses beauty and illusion to achieve divine purposes.
  • E. Swargarohini
    Swargarohini is a prominent Himalayan peak in the Garhwal region of Uttarakhand, India, renowned for its dramatic, multi-summited massif and challenging climbing routes.
  • 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_69e0b509a318819092fbbcb21d1fe603 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7210110a48190a6359b6732f6293d completed April 21, 2026, 7:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965e013388190a058d84063e22694 completed May 17, 2026, 6:53 a.m.
Created at: April 16, 2026, 2:54 p.m.