Triple

T20851054
Position Surface form Disambiguated ID Type / Status
Subject Suketi Khad E513362 entity
Predicate region P40 FINISHED
Object Mandi division 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: Mandi division | Statement: [Suketi Khad, region, Mandi division]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandi division
Context triple: [Suketi Khad, region, Mandi division]
  • A. Mandi division chosen
    Mandi division is an administrative division in the Indian state of Himachal Pradesh that oversees multiple districts, including Mandi district.
  • B. Mandi district
    Mandi district is an administrative region in the Indian state of Himachal Pradesh, known for its hilly terrain, temples, and location in the central part of the state.
  • C. Alwar division
    Alwar division is an administrative division in the Indian state of Rajasthan that encompasses Alwar district and surrounding areas for regional governance.
  • D. Karnal division
    Karnal division is an administrative division in the Indian state of Haryana that includes districts such as Karnal and Panipat.
  • E. Ambala division
    Ambala division is an administrative division in the Indian state of Haryana that oversees several districts in the northern part of the state.
  • 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_69e0b4f4898081908209e58edb8f9c45 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a3d8808190b8efce77ae36850e completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:43 p.m.