Triple

T27416312
Position Surface form Disambiguated ID Type / Status
Subject Hindu epics E692903 entity
Predicate traditionallyWrittenIn P23831 FINISHED
Object Sanskrit 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: Sanskrit | Statement: [Hindu epics, traditionallyWrittenIn, Sanskrit]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: traditionallyWrittenIn
Context triple: [Hindu epics, traditionallyWrittenIn, Sanskrit]
  • A. isWrittenWith
    Indicates that something is created or expressed using a particular writing tool, medium, or system.
  • B. currentlyWrittenIn chosen
    Indicates that a work or document is, at the present time, expressed or composed in a particular language or writing system.
  • C. hasWritingTraditionVia
    Indicates that an entity possesses or participates in a writing tradition by means of, or through the mediation of, another specified entity or method.
  • D. canBeWrittenIn
    Indicates that something is capable of being expressed, encoded, or represented using a particular language, notation, or medium.
  • E. writingSystemUsedIn
    Indicates that a particular writing system is employed for written communication within a given language, region, or context.
  • 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_69ef5208617081908f731d312e0fd1bc completed April 27, 2026, 12:09 p.m.
NER Named-entity recognition batch_69fb2e940d5c8190bceae77daf4ef512 completed May 6, 2026, 12:05 p.m.
PD Predicate disambiguation batch_69f9fec70bd881909c658a3c5020318b completed May 5, 2026, 2:29 p.m.
Created at: April 27, 2026, 12:34 p.m.