Triple

T14882637
Position Surface form Disambiguated ID Type / Status
Subject Hindu varna system E350037 entity
Predicate describedInText P519 FINISHED
Object Rigveda E18873 NE FINISHED

How this triple was built (3 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: [Hindu varna system, describedInText, Rigveda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rigveda
Context triple: [Hindu varna system, describedInText, 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.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: describedInText
Context triple: [Hindu varna system, describedInText, Rigveda]
  • A. describedIn chosen
    Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
  • B. describes
    Indicates that one entity provides an explanation, representation, or account of another entity or concept.
  • C. hasDescription
    Indicates that an entity is associated with a textual description that explains or characterizes it.
  • D. eraDescribed
    Indicates that a subject provides a description or characterization of a particular historical or temporal era.
  • E. describedByAuthorAs
    Indicates that one entity is characterized, labeled, or portrayed in a particular way by an author.
  • F. None of above.

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_69d822ee4f408190b6ac3b2fa434f0df completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded5e7c0e48190af2d68a71130585c completed April 15, 2026, 12:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe6b5af8208190a35451477ea20b03 completed May 8, 2026, 11:01 p.m.
PD Predicate disambiguation batch_69de8c1a2bcc81908f914e2e2ced65eb completed April 14, 2026, 6:48 p.m.
Created at: April 10, 2026, 1:56 a.m.