Triple

T932869
Position Surface form Disambiguated ID Type / Status
Subject Atharvaveda E20131 entity
Predicate relatedTo P37 FINISHED
Object Samaveda E19932 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: Samaveda | Statement: [Atharvaveda, relatedTo, Samaveda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samaveda
Context triple: [Atharvaveda, relatedTo, Samaveda]
  • A. Samaveda chosen
    Samaveda is one of the four Vedas of ancient Indian scripture, primarily consisting of melodies and chants used in Vedic rituals and early Hindu liturgy.
  • B. Atharvaveda
    Atharvaveda is one of the four Vedas of Hinduism, comprising hymns, spells, and rituals dealing with everyday life, healing, and protection.
  • 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. Shukla Yajurveda
    Shukla Yajurveda is one of the two main recensions of the Yajurveda, characterized by its clear separation of mantras and explanatory prose used in Vedic ritual.
  • E. Krishna Yajurveda
    Krishna Yajurveda is the "Black" recension of the Yajurveda, a Vedic Sanskrit text that intermingles prose mantras and explanatory Brahmana material used primarily in ritual contexts.
  • 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_69a493af3dc48190adb7263e6e445ea1 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b34c457c819085cbfa0c798cb4c6 completed March 1, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69acb2f040948190b19ce68fff879637 completed March 7, 2026, 11:21 p.m.
Created at: March 1, 2026, 7:40 p.m.