Triple

T20547718
Position Surface form Disambiguated ID Type / Status
Subject Kanpur Airport E504514 entity
Predicate IATACode P418 FINISHED
Object KNU 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: KNU | Statement: [Kanpur Airport, IATACode, KNU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KNU
Context triple: [Kanpur Airport, IATACode, KNU]
  • A. KNU
    KNU is a leading Ukrainian public research university located in Kyiv, widely regarded as one of the country’s most prestigious higher education institutions.
  • B. KNU
    KNU is a public university located in Asansol, West Bengal, India, known for offering a range of undergraduate and postgraduate programs across arts, science, commerce, and professional disciplines.
  • C. KNU
    KNU is a major national research university in Daegu, South Korea, known for its comprehensive academic programs and strong emphasis on science and technology.
  • D. KNU chosen
    KNU is the IATA airport code assigned to Kanpur Airport in Kanpur, India.
  • E. KNU
    KNU is a political organization and ethnic armed group representing the Karen people in Myanmar, long involved in one of the world’s longest-running insurgencies against the central government.
  • 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_69e0b4b52c048190952b4d0f430813a3 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a2991ac8819089b8c2d70eb88952 completed April 20, 2026, 10:03 p.m.
Created at: April 16, 2026, 11:38 a.m.