Triple
T33958977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DFW Airport Skylink |
E870655
|
entity |
| Predicate | locatedAirsideOrLandside |
P161319
|
FINISHED |
| Object | airside |
—
|
LITERAL 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: airside | Statement: [DFW Airport Skylink, locatedAirsideOrLandside, airside]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedAirsideOrLandside Context triple: [DFW Airport Skylink, locatedAirsideOrLandside, airside]
-
A.
isAirside
chosen
Indicates that something is located within the secure, restricted-access area of an airport beyond security checkpoints, typically accessible only to authorized personnel and ticketed passengers.
-
B.
hasLandsideConnection
Indicates that two locations are connected by a route or access on land, allowing movement between them without using air or water transport.
-
C.
hasLandsideArea
Indicates that one entity includes or is associated with a landside area, typically the non-airside portion of a transport or terminal facility.
-
D.
locatedInAirportArea
Indicates that something is situated within the grounds or designated area of an airport.
-
E.
isLocatedAtAirportType
Indicates that one entity is situated at, or associated with, an airport of a specified type (e.g., international, regional, military).
- 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_69f3499c2d7481909c953a5010227725 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a037c8ae0248190b7e2ce4bf852c22d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379f963908190846d232f386fd98f |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:49 a.m.