Triple

T5582979
Position Surface form Disambiguated ID Type / Status
Subject Kaushītaki Upanishad E146683 entity
Predicate belongsTo P35 FINISHED
Object Rigvedic corpus E18873 NE 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: Rigvedic corpus | Statement: [Kaushītaki Upanishad, belongsTo, Rigvedic corpus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rigvedic corpus
Context triple: [Kaushītaki Upanishad, belongsTo, Rigvedic corpus]
  • A. Vedas
    The Vedas are a collection of ancient sacred texts composed in Sanskrit that form the foundational spiritual and philosophical scriptures of Hinduism.
  • B. Rigveda chosen
    The Rigveda is the oldest of the four Vedas, a foundational collection of ancient Sanskrit hymns that form a core sacred text of Hinduism.
  • C. Yajurveda
    Yajurveda is one of the four principal Vedas of Hinduism, primarily focused on prose mantras and ritual formulas used in sacrificial ceremonies.
  • D. Vedic Sanskrit
    Vedic Sanskrit is the ancient form of the Sanskrit language used in the Vedas, characterized by archaic grammar, rich oral tradition, and its role as one of the earliest attested Indo-European languages.
  • E. Jatavedas
    Jatavedas is a prominent Vedic epithet of the fire god Agni, highlighting his all-knowing, all-consuming nature as the divine flame that permeates and witnesses all.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69c0090287a08190b4098411effe970c completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0208333f08190bf0049b6bdd280f5 completed March 22, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0285e7bc08190bd5a08c50679e9d9 completed March 22, 2026, 5:35 p.m.
Created at: March 22, 2026, 3:37 p.m.