Triple

T20412803
Position Surface form Disambiguated ID Type / Status
Subject Kamakshi Amman Temple E500630 entity
Predicate hasShrineFor P27875 FINISHED
Object Durga 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: Durga | Statement: [Kamakshi Amman Temple, hasShrineFor, Durga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Durga
Context triple: [Kamakshi Amman Temple, hasShrineFor, Durga]
  • A. Durga
    Durga is a central character in Bibhutibhushan Bandyopadhyay’s novel and Satyajit Ray’s film adaptation "Pather Panchali," depicted as a spirited, mischievous young girl growing up in rural Bengal.
  • B. Goddess Durga chosen
    Goddess Durga is a principal Hindu deity revered as a fierce yet protective mother goddess who embodies divine strength, righteousness, and the destruction of evil.
  • C. Durga Bhagwati
    Durga Bhagwati is a town located in Nepal's Madhesh Province.
  • D. Durga Rani
    Durga Rani, better known as Durga Bhabhi, was an Indian revolutionary and freedom fighter associated with the Hindustan Socialist Republican Association during the struggle against British rule.
  • E. Bhudevi
    Bhudevi is the Hindu earth goddess and consort of Lord Vishnu, revered as the personification of the fertile, nurturing aspects of the Earth.
  • 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a417f208190be9bc11650ee0a87 completed April 20, 2026, 7:10 p.m.
Created at: April 16, 2026, 11:30 a.m.