Triple

T17625298
Position Surface form Disambiguated ID Type / Status
Subject Runway 6/24 E429824 entity
Predicate hasICAOCodeOfAirport P419 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 6/24, hasICAOCodeOfAirport, KISP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: KISP
Context triple: [Runway 6/24, hasICAOCodeOfAirport, 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46dbc62e88190b9757dc7c52d7fee completed April 19, 2026, 5:53 a.m.
Created at: April 10, 2026, 5:52 a.m.