Triple

T20170818
Position Surface form Disambiguated ID Type / Status
Subject Ashok Kumar E491951 entity
Predicate child P120 FINISHED
Object Bharti Jaffrey 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: Bharti Jaffrey | Statement: [Ashok Kumar, child, Bharti Jaffrey]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bharti Jaffrey
Context triple: [Ashok Kumar, child, Bharti Jaffrey]
  • A. Madhur Jaffrey
    Madhur Jaffrey is an Indian-born actress and influential food and travel writer widely credited with popularizing Indian cuisine in the Western world.
  • B. Sakina Jaffrey chosen
    Sakina Jaffrey is an American actress known for her roles in television series such as House of Cards, Timeless, and Billions, as well as numerous film and stage appearances.
  • C. Manjula Ghattamaneni
    Manjula Ghattamaneni is an Indian film producer and actress primarily associated with Telugu cinema and a member of the prominent Ghattamaneni film family.
  • D. Nina Khosla
    Nina Khosla is a designer and entrepreneur known for her work at the intersection of technology, product design, and venture-backed startups.
  • E. Devi Parikh
    Devi Parikh is a computer vision and AI researcher known for her work on visual question answering, human-AI collaboration, and interpretable machine learning.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66847ed9481908e6b23b399fa7005 completed April 20, 2026, 5:54 p.m.
Created at: April 11, 2026, 11:35 p.m.