Triple
T22261523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Phoenix Goodyear Airport |
E550237
|
entity |
| Predicate | ICAOCode |
P419
|
FINISHED |
| Object | KGYR |
—
|
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: KGYR | Statement: [Phoenix Goodyear Airport, ICAOCode, KGYR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KGYR Context triple: [Phoenix Goodyear Airport, ICAOCode, KGYR]
-
A.
KGYR
chosen
KGYR is the ICAO airport code for Phoenix Goodyear Airport, a public airport serving the Goodyear area near Phoenix, Arizona.
-
B.
KGYI
KGYI is the ICAO airport code for North Texas Regional Airport, a public airport serving the Sherman–Denison area in Texas, United States.
-
C.
KGKY
KGKY is the ICAO airport code for Arlington Municipal Airport in Arlington, Texas, a public airport serving general aviation.
-
D.
KGYY
KGYY is the ICAO airport code for Gary/Chicago International Airport, a public airport serving the Gary, Indiana and greater Chicago metropolitan area.
-
E.
KGCY
KGCY is the ICAO airport code for Greeneville–Greene County Municipal Airport, a public airport serving Greeneville in Greene County, Tennessee, 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_69e11e42adb8819087714772ea606709 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f141b87de0819088b7553406343068 |
completed | April 28, 2026, 11:24 p.m. |
Created at: April 16, 2026, 8:39 p.m.