Triple
T17600026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Concourse A (Norfolk International Airport) |
E428668
|
entity |
| Predicate | hasICAOCodeOfAirport |
P419
|
FINISHED |
| Object | KORF |
—
|
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: KORF | Statement: [Concourse A (Norfolk International Airport), hasICAOCodeOfAirport, KORF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KORF Context triple: [Concourse A (Norfolk International Airport), hasICAOCodeOfAirport, KORF]
-
A.
KORF
chosen
KORF is the ICAO airport code for Norfolk International Airport, a major commercial airport serving the Hampton Roads region of Virginia, USA.
-
B.
KORL
KORL is the ICAO airport code for Orlando Executive Airport, a public airport serving the Orlando, Florida area.
-
C.
KOR
KOR is the ICAO airline designator assigned to Air Koryo, the state-owned national carrier of North Korea.
-
D.
KOR
KOR is the FIFA country code representing the South Korea national football team in international competitions.
-
E.
Kors
Kors is the surname of American fashion designer Michael Kors, known for his eponymous luxury brand.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4812d48190bf8e899fa8f7fbe4 |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.