Triple

T18068702
Position Surface form Disambiguated ID Type / Status
Subject Runway 15L/33R E432360 entity
Predicate belongsToAirport P18358 FINISHED
Object KISP 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: KISP | Statement: [Runway 15L/33R, belongsToAirport, KISP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KISP
Context triple: [Runway 15L/33R, belongsToAirport, KISP]
  • A. KISP chosen
    KISP is the ICAO airport code for Long Island MacArthur Airport, a public airport serving Long Island in New York.
  • B. KIS
    KIS is the IATA airport code for Kisumu International Airport, a key air transport hub serving the city of Kisumu in western Kenya.
  • C. KISA
    KISA is the Korea Internet & Security Agency, a government-affiliated organization that manages South Korea’s internet infrastructure and cybersecurity, including administration of the .kr country-code top-level domain.
  • D. KSPI
    KSPI is the ICAO airport code for Abraham Lincoln Capital Airport in Springfield, Illinois, United States.
  • E. KISM
    KISM is the ICAO airport code for Kissimmee Gateway Airport, a public airport serving the Kissimmee area in Florida, United States.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ccebff748190b41d2edd93994c67 completed April 19, 2026, 12:39 p.m.
Created at: April 10, 2026, 10:26 a.m.