Triple

T5375132
Position Surface form Disambiguated ID Type / Status
Subject Valmiki E108941 entity
Predicate ValmikiJayantiObservedOn P22837 FINISHED
Object Ashwin Purnima (full moon of Ashwin, traditional) 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: Ashwin Purnima (full moon of Ashwin, traditional) | Statement: [Valmiki, ValmikiJayantiObservedOn, Ashwin Purnima (full moon of Ashwin, traditional)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ValmikiJayantiObservedOn
Context triple: [Valmiki, ValmikiJayantiObservedOn, Ashwin Purnima (full moon of Ashwin, traditional)]
  • A. inRamayana
    Indicates that the subject participates in, appears within, or is otherwise part of the events or narrative of the Ramayana.
  • B. VajranabhaIs
    Indicates that something or someone is identified as or characterized by being Vajranabha.
  • C. viewOnMahabharata
    Indicates a stance, interpretation, or perspective that someone holds regarding the Mahabharata.
  • D. hasPositionInMahabharata
    Indicates that one entity holds or is assigned a specific role, rank, or position within the context of the Mahabharata narrative.
  • E. monthInHinduCalendar chosen
    Indicates that a specified time or event falls within a particular month as defined by the Hindu calendar system.
  • 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_69bd440c77948190aad2a5f39b7b80f5 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd88801b188190b9ac35ed89167fa3 completed March 20, 2026, 5:48 p.m.
PD Predicate disambiguation batch_69bd846172788190969f24bc7503c05e completed March 20, 2026, 5:31 p.m.
Created at: March 20, 2026, 2:03 p.m.