Triple

T22537669
Position Surface form Disambiguated ID Type / Status
Subject Yakutsk Airport E557198 entity
Predicate IATACode P418 FINISHED
Object YKS 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: YKS | Statement: [Yakutsk Airport, IATACode, YKS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: YKS
Context triple: [Yakutsk Airport, IATACode, YKS]
  • A. YKS chosen
    YKS is the IATA airport code for Yakutsk Airport, the main air gateway to the city of Yakutsk in Russia’s Sakha Republic.
  • B. Gaokao
    Gaokao is China’s highly competitive national college entrance examination that largely determines students’ access to universities and future educational opportunities.
  • C. Iranian University Entrance Exam (Konkur)
    The Iranian University Entrance Exam (Konkur) is a highly competitive, nationwide standardized test that determines admission to most undergraduate programs in Iran’s public universities.
  • D. LYS
    LYS is the IATA airport code for Lyon–Saint-Exupéry Airport, the main international airport serving the Lyon metropolitan area in France.
  • E. LYS
    LYS is the station code for Lysaker Station, a key railway hub in the Oslo metropolitan area of Norway.
  • 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_69e11e57483c8190b0887c4f8ff26446 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f2f671c8190b7a7d9b6d0d64a9b completed April 29, 2026, 1:30 a.m.
Created at: April 16, 2026, 8:51 p.m.