Triple

T11695018
Position Surface form Disambiguated ID Type / Status
Subject Sanjay Kapoor E277970 entity
Predicate relative P37 FINISHED
Object Janhvi Kapoor E743343 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: Janhvi Kapoor | Statement: [Sanjay Kapoor, relative, Janhvi Kapoor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janhvi Kapoor
Context triple: [Sanjay Kapoor, relative, Janhvi Kapoor]
  • A. Janhvi Kapoor chosen
    Janhvi Kapoor is an Indian film actress who works primarily in Hindi cinema and is known for being one of the prominent young stars in Bollywood.
  • B. Sanjana Kapoor
    Sanjana Kapoor is an Indian theatre personality and former film actress known for her work with Mumbai’s Prithvi Theatre and for promoting theatre education and outreach.
  • C. Syesha Kapoor
    Syesha Kapoor is the daughter of renowned Indian playback singer Alka Yagnik.
  • D. Shriya Saran
    Shriya Saran is an Indian actress and model known for her work in Telugu, Tamil, and Hindi cinema, appearing in numerous commercially successful and critically acclaimed films.
  • E. Aditi Rao Hydari
    Aditi Rao Hydari is an Indian actress and classical dancer known for her work in Hindi, Tamil, Telugu, and Malayalam films, often praised for her expressive performances and graceful screen presence.
  • 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_69d6aafe02d881909900d54ad7d4af84 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a47b9eb48190976a35e91e25b56b completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef833084988190b5004c93f68dc628 completed April 27, 2026, 3:39 p.m.
Created at: April 8, 2026, 9:40 p.m.