Triple

T8362897
Position Surface form Disambiguated ID Type / Status
Subject Ola E197052 entity
Predicate founder P104 FINISHED
Object Ankit Bhati E192549 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: Ankit Bhati | Statement: [Ola, founder, Ankit Bhati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ankit Bhati
Context triple: [Ola, founder, Ankit Bhati]
  • A. Ankit Bhati chosen
    Ankit Bhati is an Indian entrepreneur best known as the co-founder and former Chief Technology Officer of the ride-hailing company Ola.
  • B. Abhishek Verma
    Abhishek Verma is a computer scientist best known as a co-creator of Google Borg, the large-scale cluster management and scheduling system that inspired Kubernetes.
  • C. Anshu Jain
    Anshu Jain was a prominent investment banker best known as the former co-CEO of Deutsche Bank and later a senior executive at Cantor Fitzgerald.
  • D. Bhavish Aggarwal
    Bhavish Aggarwal is an Indian entrepreneur best known for co-founding and leading the ride-hailing and mobility company Ola.
  • E. Rahul Bhatia
    Rahul Bhatia is an Indian businessman best known as the co-founder and key architect of IndiGo’s rise into India’s largest low-cost airline.
  • 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_69ca82f2dbe48190aba982e75a0d94de completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb80768b208190a5f6c9e6cb6e7f30 completed March 31, 2026, 8:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69cde7c747b48190b1979b4eaf281df5 completed April 2, 2026, 3:51 a.m.
Created at: March 30, 2026, 6 p.m.