Triple

T36515072
Position Surface form Disambiguated ID Type / Status
Subject Sachin Bansal E900012 entity
Predicate roleAtNavi P168974 FINISHED
Object co-founder and managing director LITERAL 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: co-founder and managing director | Statement: [Sachin Bansal, roleAtNavi, co-founder and managing director]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleAtNavi
Context triple: [Sachin Bansal, roleAtNavi, co-founder and managing director]
  • A. roleOn
    Indicates that an entity holds or performs a specific role or function within another entity, context, or activity.
  • B. roleOnPern
    Indicates the specific function, position, or duty an entity holds within the context of Pern.
  • C. roleAccordingTo
    Indicates that an entity holds a particular role or function as defined or interpreted by a specified source or perspective.
  • D. roleAtGV chosen
    Indicates that an entity holds or held a specific role or position at a particular organization, institution, or venue referred to as GV.
  • E. roleInPath
    Indicates that an entity participates in a specific path or route by occupying a particular role or position within that path.
  • F. None of above.

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_69f76e5dada881909da2d34bc7a9202a completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69f7cec454a88190a9f3bbee2b856636 completed May 3, 2026, 10:40 p.m.
PD Predicate disambiguation batch_69f7c8977c288190997a892ec5f756ed completed May 3, 2026, 10:13 p.m.
Created at: May 3, 2026, 4:10 p.m.