Triple
T17548183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doncaster Sheffield Airport |
E427384
|
entity |
| Predicate | ICAOcode |
P419
|
FINISHED |
| Object | EGCN |
—
|
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: EGCN | Statement: [Doncaster Sheffield Airport, ICAOcode, EGCN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: EGCN Context triple: [Doncaster Sheffield Airport, ICAOcode, EGCN]
-
A.
EGCN
chosen
EGCN is the ICAO airport code for Doncaster Sheffield Airport, a former international airport in South Yorkshire, England.
-
B.
DGL
DGL is the National Rail station code for Dingle Road railway station in Penarth, Wales.
-
C.
DGL
DGL is the vehicle registration code assigned to the town of Głogów in Poland.
-
D.
GCN
GCN (Graphics Core Next) is AMD's GPU microarchitecture designed to improve parallel processing performance and efficiency in graphics and compute workloads.
-
E.
GCN
GCN is the airport code for Grand Canyon National Park Airport, a regional airport serving the Grand Canyon area near Tusayan, Arizona.
- 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_69d889df6dc081908f67dbadc03c07ee |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e454631e148190a1d46a6ecb79c71a |
completed | April 19, 2026, 4:04 a.m. |
Created at: April 10, 2026, 5:49 a.m.