Triple

T22591184
Position Surface form Disambiguated ID Type / Status
Subject Hindu pantheon E564951 entity
Predicate hasDeity P5606 FINISHED
Object Kurma NE NERFINISHED

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: Kurma | Statement: [Hindu pantheon, hasDeity, Kurma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurma
Context triple: [Hindu pantheon, hasDeity, Kurma]
  • A. Kurma chosen
    Kurma is the turtle incarnation of the Hindu god Vishnu, known for supporting Mount Mandara during the churning of the cosmic ocean.
  • B. Kukshi
    Kukshi is a town in the Dhar district of Madhya Pradesh, India, known as a commercial and agricultural hub in the Malwa region.
  • C. Kekaya
    Kekaya was an ancient kingdom in the Indian epic tradition, known as the realm of King Ashwapati and associated with the region of northwestern India.
  • D. Kuku
    Kuku are an ethnic group native to South Sudan, primarily inhabiting parts of Central Equatoria and speaking a Bari-related language.
  • E. Kurmi
    Kurmi is an agricultural caste community of northern and eastern India, traditionally known as skilled cultivators and landholders.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f16160651081909d23735336fd7a16 completed April 29, 2026, 1:39 a.m.
Created at: April 17, 2026, 2:48 p.m.