Triple

T5241458
Position Surface form Disambiguated ID Type / Status
Subject Ujjain E118350 entity
Predicate locatedOn P40 FINISHED
Object Shipra River E160046 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: Shipra River | Statement: [Ujjain, locatedOn, Shipra River]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shipra River
Context triple: [Ujjain, locatedOn, Shipra River]
  • A. Shipra River chosen
    The Shipra River is a sacred river in central India, especially revered in the city of Ujjain where it is central to major Hindu religious festivals such as the Kumbh Mela.
  • B. Haldi River
    The Haldi River is a river in the Indian state of West Bengal that joins the Hooghly River and forms part of the lower Ganges river system.
  • C. Satna River
    Satna River is a river in central India that flows through the Satna district of Madhya Pradesh and serves as an important local water source.
  • D. Kothari River
    The Kothari River is a tributary river in the Indian state of Rajasthan that contributes to the Banas River system and supports local agriculture and settlements along its course.
  • E. Yantra River
    The Yantra River is a significant river in northern Bulgaria that flows through historic towns like Veliko Tarnovo before joining the Danube.
  • 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_69bd4467db0881909b3b0982df32cc8f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd7b2c50508190b84bab216c30cbfe completed March 20, 2026, 4:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69c81e93671481909555acbc8a712930 completed March 28, 2026, 6:31 p.m.
Created at: March 20, 2026, 1:49 p.m.