Triple

T6678739
Position Surface form Disambiguated ID Type / Status
Subject Marichi E151923 entity
Predicate mentionedIn P831 FINISHED
Object Rigveda 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: Rigveda | Statement: [Marichi, mentionedIn, Rigveda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rigveda
Context triple: [Marichi, mentionedIn, Rigveda]
  • A. 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.
  • B. Vedas
    The Vedas are a collection of ancient sacred texts composed in Sanskrit that form the foundational spiritual and philosophical scriptures 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. Vālmīki
    Vālmīki is the revered ancient Indian sage traditionally credited as the author of the Sanskrit epic Ramayana.
  • 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_69c687f830bc81909eb8b04dbb8450b1 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b0f6813c8190906f619b4276a232 completed March 27, 2026, 4:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6f7a9fda4819096d4bd3e8133cecb completed March 27, 2026, 9:33 p.m.
Created at: March 27, 2026, 2:03 p.m.