Triple

T15300085
Position Surface form Disambiguated ID Type / Status
Subject Tolmachevo Airport E365762 entity
Predicate ICAO code P419 FINISHED
Object UNNT E838833 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: UNNT | Statement: [Tolmachevo Airport, ICAO code, UNNT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UNNT
Context triple: [Tolmachevo Airport, ICAO code, UNNT]
  • A. UNNT chosen
    UNNT is the ICAO airport code for Tolmachevo Airport, the main international airport serving Novosibirsk in Russia.
  • B. UNNC
    UNNC is the University of Nottingham Ningbo China, a Sino-foreign joint university located in Ningbo, Zhejiang Province, offering British-style higher education in China.
  • C. UNN
    UNN is the commonly used acronym for the University of Nigeria, Nsukka, one of Nigeria’s leading federal universities.
  • D. UNNM
    UNNM is the acronym for the United Nations Network on Migration, a UN coordination mechanism focused on safe, orderly, and regular migration.
  • E. UNT
    UNT is the commonly used acronym for the National University of Trujillo, a public higher education institution in Trujillo, Peru.
  • 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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0368869f8819098cf9e7801e37548 completed April 16, 2026, 1:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69feef8513a08190b2d2a7dde85dd43d completed May 9, 2026, 8:25 a.m.
Created at: April 10, 2026, 3:15 a.m.