Triple

T6971327
Position Surface form Disambiguated ID Type / Status
Subject Kumara E161604 entity
Predicate hasName P744 FINISHED
Object Saravanabhava E161605 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: Saravanabhava | Statement: [Kumara, hasName, Saravanabhava]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saravanabhava
Context triple: [Kumara, hasName, Saravanabhava]
  • A. Saravanabhava chosen
    Saravanabhava is an epithet of the Hindu god Kartikeya (Murugan), highlighting his mythological birth in the reeds of the Saravana lake.
  • B. Satvata
    Satvata is an ancient subgroup of the Yadava clan in Indian tradition, often associated with early Vaishnavism and the worship of Krishna.
  • C. Suyodhana
    Suyodhana is another name for Duryodhana, the primary Kaurava antagonist in the Indian epic Mahabharata.
  • D. Śivadṛṣṭi
    Śivadṛṣṭi is a foundational philosophical treatise of non-dual Shaiva (Kashmir Shaivism) thought, in which Somānanda systematically expounds a monistic theology centered on Śiva as ultimate reality.
  • E. Kesava
    Kesava is a revered epithet of the Hindu god Vishnu, highlighting him as the slayer of the demon Keshi and the one with beautiful, luxuriant hair.
  • 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_69c68854a0d88190bc0bf82263f1afce completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6db38013081908037d23843dccad7 completed March 27, 2026, 7:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69c761a2b2f481908718b4803cfbfae9 completed March 28, 2026, 5:05 a.m.
Created at: March 27, 2026, 2:30 p.m.