Triple
T27427405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RAF Ayr |
E690526
|
entity |
| Predicate | hasNearbyCivilAirport |
P94103
|
FINISHED |
| Object | Glasgow Prestwick Airport |
—
|
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: Glasgow Prestwick Airport | Statement: [RAF Ayr, hasNearbyCivilAirport, Glasgow Prestwick Airport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyCivilAirport Context triple: [RAF Ayr, hasNearbyCivilAirport, Glasgow Prestwick Airport]
-
A.
nearestAirport
Indicates that one airport is the closest in distance to a given location or entity compared to all other airports.
-
B.
nearbyAirportRelationship
chosen
Indicates that one location has an airport situated close enough to serve it conveniently, establishing a nearby-airport relationship between the two.
-
C.
hasAirportInVicinity
Indicates that an entity is located near or served by an airport in its surrounding area.
-
D.
nearestLargerAirport
Indicates that one airport is the closest geographically among all airports that are larger (e.g., by traffic or capacity) than a given reference airport.
-
E.
nearbyAirportAccess
Indicates that an entity has convenient access to an airport located within a short distance or travel time.
- F. None of above.
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_69ef52003fb48190b0f1295246182a86 |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69fce7671f108190bf3ebf54339068b5 |
completed | May 7, 2026, 7:26 p.m. |
| PD | Predicate disambiguation | batch_69fce5b5a84c81908ac1b5b9f08d48d0 |
completed | May 7, 2026, 7:19 p.m. |
Created at: April 27, 2026, 12:41 p.m.