Triple
T7768672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mackinac Island Airport |
E179013
|
entity |
| Predicate | has runway |
P67502
|
FINISHED |
| Object | Runway 8/26 |
—
|
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: Runway 8/26 | Statement: [Mackinac Island Airport, has runway, Runway 8/26]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: has runway Context triple: [Mackinac Island Airport, has runway, Runway 8/26]
-
A.
runway
Indicates a relationship where a runway serves as the takeoff and landing surface used by aircraft at an airport or airfield.
-
B.
hasRunwayType
Indicates that an airport or airfield has a runway of a specified type or surface classification.
-
C.
hasRunwayCount
Indicates the number of runways that a given entity (such as an airport) possesses.
-
D.
isRunwayOf
chosen
Indicates that a physical runway is a component or facility belonging to, used by, or officially associated with a particular airport or airfield.
-
E.
hasRunwayNumber
Indicates that an airport or airfield runway is assigned a specific identifying number.
- 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_69c69f30602c819082ab52cd4af5c592 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c704376dc08190890f5ebb9f259cfd |
completed | March 27, 2026, 10:27 p.m. |
| PD | Predicate disambiguation | batch_69c7016f4ce881909c2e9f610255187b |
completed | March 27, 2026, 10:15 p.m. |
Created at: March 27, 2026, 4:11 p.m.