Triple

T874023
Position Surface form Disambiguated ID Type / Status
Subject Brahma E18875 entity
Predicate scripturalMention P4481 FINISHED
Object Puranas E18563 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: Puranas | Statement: [Brahma, scripturalMention, Puranas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Puranas
Context triple: [Brahma, scripturalMention, Puranas]
  • A. Puranas chosen
    The Puranas are a genre of ancient and medieval Hindu texts that narrate cosmology, myths, legends of gods and heroes, and traditional religious practices and teachings.
  • 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. Smriti literature
    Smriti literature is a body of post-Vedic Hindu texts, including legal, ethical, and social codes such as the Dharmashastras, that guide religious practice and daily life.
  • D. Upanishads
    The Upanishads are a collection of ancient Indian philosophical texts that explore the nature of ultimate reality (Brahman), the self (Atman), and the path to spiritual liberation, forming a foundational component of Hindu thought.
  • E. Kakawin Smaradahana
    Kakawin Smaradahana is a classical Old Javanese epic poem from the Kediri period, renowned for its romantic and courtly themes and its influence on later Javanese and Balinese literature.
  • 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: scripturalMention
Context triple: [Brahma, scripturalMention, Puranas]
  • A. scripturalReference
    Indicates that one entity cites, alludes to, or is based on a specific passage or portion of a scriptural text found in another entity.
  • B. scripturalAllusion chosen
    Indicates that one entity references, echoes, or draws upon content, themes, or language from a scriptural or sacred text in relation to another entity.
  • C. scriptureAllusion
    Indicates that one entity makes reference to, echoes, or is inspired by a passage, theme, or element from a scriptural text found in another entity.
  • D. scripturalBasis
    Indicates that one entity serves as the religious or scriptural foundation, support, or justification for another entity (such as a belief, practice, or doctrine).
  • E. hasScripture
    Indicates that one entity possesses, is associated with, or is defined by a particular scripture or set of scriptural texts.
  • 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_69a4938db1f081909bcd1ad2713b6096 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4ac992d8c819088800f5a713fa7a4 completed March 1, 2026, 9:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69a7c01af9608190b3b735c590024f03 completed March 4, 2026, 5:16 a.m.
PD Predicate disambiguation batch_69a4aa8b9b5c81909ac71904f8b8b5cd completed March 1, 2026, 9:07 p.m.
Created at: March 1, 2026, 7:39 p.m.