Triple
T17871259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deering Airport |
E446840
|
entity |
| Predicate | FAACode |
P420
|
FINISHED |
| Object | DEE |
—
|
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: DEE | Statement: [Deering Airport, FAACode, DEE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: DEE Context triple: [Deering Airport, FAACode, DEE]
-
A.
DEE
chosen
DEE is the IATA airport code for Yuzhno-Kurilsk Mendeleyevo Airport, which serves the town of Yuzhno-Kurilsk in Russia’s Kuril Islands.
-
B.
DEECA
DEECA is the Victorian government department responsible for energy policy, environmental protection, and climate action in the state of Victoria, Australia.
-
C.
DEB
DEB is the abbreviation for the Deutscher Eishockey-Bund, the governing body for ice hockey in Germany.
-
D.
DEB
DEB is the IATA airport code for Debrecen International Airport in Debrecen, Hungary.
-
E.
DEEP
DEEP is a Japanese mixed martial arts promotion known for hosting regional events and developing fighters who later compete in major international organizations.
- 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_69d8b9f4c22c819093c2680434472894 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49aa30ff8819090c51c1d7767e952 |
completed | April 19, 2026, 9:04 a.m. |
Created at: April 10, 2026, 10:18 a.m.