Triple

T19429284
Position Surface form Disambiguated ID Type / Status
Subject Keshi E486066 entity
Predicate epithetRelation P121211 FINISHED
Object slaying of Keshi is source of Krishna epithet Kesava 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: slaying of Keshi is source of Krishna epithet Kesava | Statement: [Keshi, epithetRelation, slaying of Keshi is source of Krishna epithet Kesava]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: epithetRelation
Context triple: [Keshi, epithetRelation, slaying of Keshi is source of Krishna epithet Kesava]
  • A. epithetAppliedBy
    Indicates that a particular epithet or descriptive label is used or assigned by a specific agent to a target entity.
  • B. associatedWithEpithet chosen
    Indicates that an entity is linked to or described by a particular epithet or descriptive label.
  • C. epithetScope
    Indicates that an epithet (a descriptive label or phrase) applies specifically within a defined contextual scope or domain for the referenced entity or relation.
  • D. epithetOrTitle
    Indicates that one entity serves as an epithet, honorific, or formal title used to designate or characterize another entity.
  • E. languageOfEpithet
    Indicates the language in which an epithet (such as a descriptive or honorary title) is expressed.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6321b78d08190b86cef7c60cbb61c completed April 20, 2026, 2:03 p.m.
PD Predicate disambiguation batch_69e4fd6e806081909053f325ba01ab6b completed April 19, 2026, 4:06 p.m.
Created at: April 10, 2026, 1:37 p.m.