Triple

T1691895
Position Surface form Disambiguated ID Type / Status
Subject Sangli E36566 entity
Predicate hasNearbyCity P350 FINISHED
Object Belagavi E170634 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: Belagavi | Statement: [Sangli, hasNearbyCity, Belagavi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Belagavi
Context triple: [Sangli, hasNearbyCity, Belagavi]
  • A. Belagavi chosen
    Belagavi is a major city in southwestern India known for its industrial base, educational institutions, and cultural blend of Kannada and Marathi influences.
  • B. Andhra Bhoja
    Andhra Bhoja is an honorific epithet celebrating Sri Krishnadevaraya as a great patron of Telugu literature and the arts, likening him to the legendary king Bhoja.
  • C. Yadava
    Yadava refers to the ancient Indo-Aryan clan or community traditionally regarded as the lineage of King Yadu and prominently associated with the Hindu deity Krishna.
  • D. Rajasuya
    Rajasuya is an ancient Vedic royal consecration ritual performed to legitimize and exalt a king’s sovereignty and supreme status.
  • E. Shanmukha
    Shanmukha is a revered Hindu deity of war and victory, widely worshipped as the six-faced son of Shiva and Parvati.
  • 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_69a886151508819084fa7f1ce6e05577 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62b097488190907e3bce234e3c77 completed March 6, 2026, 5:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad7996a39481909152a6a799659c93 completed March 8, 2026, 1:28 p.m.
Created at: March 4, 2026, 7:29 p.m.