Triple

T4882267
Position Surface form Disambiguated ID Type / Status
Subject Angiras sages E109356 entity
Predicate associatedWithDeity P1481 FINISHED
Object Agni E102074 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: Agni | Statement: [Angiras sages, associatedWithDeity, Agni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Agni
Context triple: [Angiras sages, associatedWithDeity, Agni]
  • A. Agni chosen
    Agni is the Vedic god of fire, revered as a central deity of sacrifice and a divine messenger between humans and the gods in ancient Indian religion.
  • B. Indra
    Indra is the king of the gods and lord of storms, war, and the heavens in ancient Vedic and Hindu mythology.
  • C. Vivasvan
    Vivasvan is a Vedic epithet of the Hindu sun god, revered as a solar deity and progenitor of humanity in ancient Indian scriptures.
  • D. Vrushabhadri
    Vrushabhadri is one of the sacred hills of the Tirumala range associated with the Tirumala Venkateswara Temple in Andhra Pradesh, India.
  • E. Savitrī
    Savitrī is a legendary heroine from the Mahābhārata renowned for her unwavering devotion and intelligence, who wins back her husband’s life from the god of death through courage and spiritual resolve.
  • 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_69bd440e9d64819083e82cf33b4d9570 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6dde6fcc8190a5aa7587f85632bd completed March 20, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69be68070bb0819095bda199cc966d31 completed March 21, 2026, 9:42 a.m.
Created at: March 20, 2026, 1:27 p.m.