Triple
T26476460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 18 |
E666049
|
entity |
| Predicate | runwayEndPosition |
P8863
|
FINISHED |
| Object | southern end of Runway 18/36 |
—
|
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: southern end of Runway 18/36 | Statement: [Runway 18, runwayEndPosition, southern end of Runway 18/36]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: runwayEndPosition Context triple: [Runway 18, runwayEndPosition, southern end of Runway 18/36]
-
A.
runwayEnd
chosen
Indicates that one entity represents the end point or terminus of a runway associated with the other entity.
-
B.
runwayEndHeading
Indicates the directional heading or bearing associated with the end of a runway, typically expressed in degrees relative to north.
-
C.
runwayAdjacentTo
Indicates that a runway is directly next to or alongside another feature or area, with no significant separation between them.
-
D.
runwayLanding
Indicates that an aircraft performs a landing operation on a specific runway.
-
E.
runwayPresence
Indicates the existence or availability of a runway at or associated with the referenced location or facility.
- 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_69ee883f80dc819090e311b022b78e02 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f6640168948190811bd5f933a87cf5 |
completed | May 2, 2026, 8:52 p.m. |
| PD | Predicate disambiguation | batch_69f6633451948190bcc0410602bb4914 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 27, 2026, 12:23 a.m.