Triple
T7768688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mackinac Island Airport |
E179013
|
entity |
| Predicate | has facility |
P12416
|
FINISHED |
| Object | terminal building |
—
|
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: terminal building | Statement: [Mackinac Island Airport, has facility, terminal building]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: has facility Context triple: [Mackinac Island Airport, has facility, terminal building]
-
A.
hasFacilities
chosen
Indicates that an entity possesses, provides, or is equipped with certain facilities or physical resources.
-
B.
hasFacilityType
Indicates that an entity possesses or is associated with a specific type or category of facility.
-
C.
servesFacility
Indicates that one entity provides services or support to a particular facility as its client, target, or area of operation.
-
D.
hasCompanyFacility
Indicates that a company possesses, operates, or is responsible for a particular facility.
-
E.
facility
Indicates that one entity is a building, installation, or physical infrastructure used to host, support, or enable the operations or activities of another entity.
- 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.