Triple

T15205232
Position Surface form Disambiguated ID Type / Status
Subject Harish Salve E363370 entity
Predicate hasChild P369 FINISHED
Object Sakshi Salve E1144991 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: Sakshi Salve | Statement: [Harish Salve, hasChild, Sakshi Salve]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sakshi Salve
Context triple: [Harish Salve, hasChild, Sakshi Salve]
  • A. Shivani Rawat
    Shivani Rawat is an Indian-American film producer and founder of ShivHans Pictures, known for backing acclaimed independent films such as Trumbo and Captain Fantastic.
  • B. Sandhini Agarwal
    Sandhini Agarwal is an AI researcher known for her work at OpenAI on safety, policy, and the development and deployment of large-scale models such as CLIP.
  • C. Geetika Jain
    Geetika Jain is known as the wife of the late Anshu Jain, the former co-CEO of Deutsche Bank.
  • D. Meenakshi Salve chosen
    Meenakshi Salve is known as the former wife of prominent Indian jurist and senior advocate Harish Salve.
  • E. Anuja Joshi
    Anuja Joshi is an Indian-American actress known for her roles in television dramas and web series, including prominent work in both Indian and American productions.
  • 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_69d85a0b78bc8190b6e5ad51a2c4cfc5 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e006b7964c8190bc8dc3444b94f15e completed April 15, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69feef687bdc819090ec8a4e1af9f422 completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 3:11 a.m.