Triple
T34171709
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aalborg Airport |
E876561
|
entity |
| Predicate | hasAirlinesOperating |
P35742
|
FINISHED |
| Object | SAS |
E245449
|
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: SAS | Statement: [Aalborg Airport, hasAirlinesOperating, SAS]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAirlinesOperating Context triple: [Aalborg Airport, hasAirlinesOperating, SAS]
-
A.
hasAirlines
chosen
Indicates that one entity (such as an airport, city, or country) is served by or associated with one or more airline operators.
-
B.
airTransportServedBy
Indicates that a particular air transport service (such as a route, flight, or airport operation) is provided or operated by a specified carrier or service provider.
-
C.
operatesFlightsInRegion
Indicates that an airline or carrier runs or provides flight services within a specified geographic region.
-
D.
servesAirlinesFrom
Indicates that a location or facility provides service or operations for flights belonging to specific airlines originating from that place.
-
E.
airLegOperatedBy
Indicates that a specific segment (leg) of an air journey is operated by a particular airline or carrier.
- F. None of above.
Provenance (4 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_69f349ad97ac8190bf1f17417c970e64 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70fe50ea881909cbdbae8c0e6946b |
completed | May 3, 2026, 9:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a36c1dab5a4819096d1acd7f9b1e3f0 |
completed | June 20, 2026, 4:37 p.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:54 a.m.