Triple

T22603813
Position Surface form Disambiguated ID Type / Status
Subject Durga Kund E574900 entity
Predicate localLanguageName P52154 FINISHED
Object दुर्गा कुंड 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: दुर्गा कुंड | Statement: [Durga Kund, localLanguageName, दुर्गा कुंड]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: दुर्गा कुंड
Context triple: [Durga Kund, localLanguageName, दुर्गा कुंड]
  • A. Durga Kund chosen
    Durga Kund is a prominent sacred pond and temple complex in Varanasi, Uttar Pradesh, dedicated to the Hindu goddess Durga and frequented by pilgrims and devotees.
  • B. Suraj Kund
    Suraj Kund is an ancient sun temple tank and sacred water reservoir located within the historic Gwalior Fort complex in Madhya Pradesh, India.
  • C. Kankali Tila
    Kankali Tila is an important archaeological mound in Mathura, India, renowned for yielding major Jain and early Mathura school of art sculptures and inscriptions.
  • D. Tulsi Ghat
    Tulsi Ghat is a prominent riverfront step area on the Ganges in Varanasi, known for its religious significance and association with the poet-saint Tulsidas.
  • E. Durga Mandir
    Durga Mandir is a prominent Hindu temple in Varanasi dedicated to the goddess Durga, known for its religious significance and distinctive red-colored architecture.
  • 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_69e245bc11308190b69d794d5d1e0bb6 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1626fad6881909895cc8c0af62f0d completed April 29, 2026, 1:44 a.m.
Created at: April 17, 2026, 2:51 p.m.