Triple
T38059715
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shanwick Oceanic FIR |
E950306
|
entity |
| Predicate | airTrafficServicesProvider |
P96239
|
FINISHED |
| Object | NATS (UK) |
—
|
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: NATS (UK) | Statement: [Shanwick Oceanic FIR, airTrafficServicesProvider, NATS (UK)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: airTrafficServicesProvider Context triple: [Shanwick Oceanic FIR, airTrafficServicesProvider, NATS (UK)]
-
A.
airTraffic
Indicates the movement and flow of aircraft through airspace, including their routes, density, and interactions while in flight.
-
B.
providesATCServiceTo
chosen
Indicates that one entity delivers air traffic control services or support to another entity.
-
C.
airTrafficRole
Indicates the specific function or responsibility an entity has within the context of air traffic operations or control.
-
D.
flightActivity
Indicates that an entity is engaged in or associated with the operation, occurrence, or status of a flight.
-
E.
affectsAirTraffic
Indicates that one entity causes changes or disruptions to the normal flow, safety, or management of air traffic.
- 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_69f76f01e63c819093b6012fc974f35a |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:21 p.m.