Triple

T22005152
Position Surface form Disambiguated ID Type / Status
Subject Translations of the Upanishads E543431 entity
Predicate scriptureCategoryTranslated P146241 FINISHED
Object Vedanta scriptures 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: Vedanta scriptures | Statement: [Translations of the Upanishads, scriptureCategoryTranslated, Vedanta scriptures]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: scriptureCategoryTranslated
Context triple: [Translations of the Upanishads, scriptureCategoryTranslated, Vedanta scriptures]
  • A. scriptureTypeTranslated
    Indicates that a scripture or sacred text has been translated into a particular type, version, or format.
  • B. scriptureTranslatedBy
    Indicates that a particular scripture has been translated by a specific agent (such as a person, group, or organization).
  • C. usedScriptureTranslation
    Indicates that one entity employed or relied on a particular translation of scripture in its actions, works, or communications.
  • D. scriptureTextEnglish
    Indicates that an entity’s associated scripture or sacred text is provided in the English language.
  • E. scriptureTraditionallyShown
    Indicates that something is traditionally depicted or represented in religious scriptures in association with something else.
  • F. None of above. chosen

Provenance (4 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_69e11e2db934819095556760c7d85e4d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1276d81e4819083a40e51249e7fd7 completed April 28, 2026, 9:32 p.m.
PD Predicate disambiguation batch_69e6f62dc9d88190ae387f145f9528de completed April 21, 2026, 3:59 a.m.
PDg Predicate description generation batch_69e6fad4a540819096cdd5ea08527220 completed April 21, 2026, 4:19 a.m.
Created at: April 16, 2026, 8:21 p.m.