Triple
T10335735
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Key West International Airport |
E242997
|
entity |
| Predicate | ICAO code |
P419
|
FINISHED |
| Object | KEYW |
E242998
|
NE FINISHED |
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: KEYW | Statement: [Key West International Airport, ICAO code, KEYW]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KEYW Context triple: [Key West International Airport, ICAO code, KEYW]
-
A.
KEYW
chosen
KEYW is the ICAO airport code for Key West International Airport, a public airport serving Key West in the Florida Keys, United States.
-
B.
KW
KW is the postcode area covering Kirkwall and much of the Orkney Islands in northern Scotland.
-
C.
KE
KE is the standard abbreviation for "Kommounistiki Epitheorisi," the theoretical and political journal associated with the Communist Party of Greece.
-
D.
KE
KE is the IATA airline designator for Korean Air, the flag carrier and largest airline of South Korea.
-
E.
KE
KE is the two-letter ISO 3166-1 alpha-2 country code assigned to Kenya for international identification and data standards.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4dfc425748190a3d29f81e32e948b |
completed | April 7, 2026, 10:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d7505b85048190ad69a4fb5c63c677 |
completed | April 9, 2026, 7:08 a.m. |
Created at: April 6, 2026, 11:53 a.m.