Triple

T18884875
Position Surface form Disambiguated ID Type / Status
Subject Prannoy Roy E461932 entity
Predicate name P16 FINISHED
Object Prannoy Roy 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: Prannoy Roy | Statement: [Prannoy Roy, name, Prannoy Roy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prannoy Roy
Context triple: [Prannoy Roy, name, Prannoy Roy]
  • A. Prannoy Roy chosen
    Prannoy Roy is an Indian economist, chartered accountant, and prominent media figure best known as the co-founder and former executive co-chairperson of the news network NDTV.
  • B. Praveen Paul
    Praveen Paul was an Indian actress known for her character roles in Malayalam cinema and theatre.
  • C. Ashok Amritraj
    Ashok Amritraj is an Indian-American film producer and former professional tennis player known for producing numerous Hollywood films across action, comedy, and drama genres.
  • D. Mahesh Bhupathi
    Mahesh Bhupathi is a former Indian professional tennis player renowned as one of the country’s most successful doubles specialists, with multiple Grand Slam titles to his name.
  • E. Pradeep Sindhu
    Pradeep Sindhu is an Indian-American computer scientist and entrepreneur best known as the co-founder and former chief technology officer of networking company Juniper Networks.
  • 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_69d8dcfc3430819095ee6fc0eb4c06a5 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c3d53e608190b8740c092b6e1523 completed April 20, 2026, 6:12 a.m.
Created at: April 10, 2026, 11:57 a.m.