Triple
T12825292
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Runway 18/36 |
E306634
|
entity |
| Predicate | runwayEnd |
P8863
|
FINISHED |
| Object | Runway 18 |
E666049
|
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: Runway 18 | Statement: [Runway 18/36, runwayEnd, Runway 18]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Runway 18 Context triple: [Runway 18/36, runwayEnd, Runway 18]
-
A.
Runway 18
chosen
Runway 18 is the southern runway end of Runway 18/36, designated for aircraft approaches and departures on a heading of approximately 180 degrees.
-
B.
Runway 15
Runway 15 is a specific landing runway used for the touchdown of NASA’s Space Shuttle mission STS-121.
-
C.
Runway 11
Runway 11 is a performance and event venue located within the AsiaWorld-Expo complex in Hong Kong.
-
D.
Runway 17
Runway 17 is a designated Space Shuttle landing runway used for the touchdown of NASA missions such as STS-26.
-
E.
Runway 23
Runway 23 is an airport runway designated for use in the approximate 230-degree magnetic heading direction, typically paired with its opposite-direction counterpart as part of a single physical runway.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf46c448190b1faa55aaacb6317 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96facb2d48190bc12efc00c9da360 |
completed | April 10, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a1a97748190992fe28c6411c4de |
completed | May 3, 2026, 8:40 a.m. |
Created at: April 9, 2026, 5:32 p.m.