Triple
T24046073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Madsen Airport |
E595521
|
entity |
| Predicate | primaryAccessModeToUnalaska |
P6529
|
FINISHED |
| Object | air transport |
—
|
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: air transport | Statement: [Tom Madsen Airport, primaryAccessModeToUnalaska, air transport]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryAccessModeToUnalaska Context triple: [Tom Madsen Airport, primaryAccessModeToUnalaska, air transport]
-
A.
secondaryAccessMode
Indicates an additional, non-primary way in which an entity can be accessed, used, or interacted with.
-
B.
accessMode
chosen
Indicates the manner or method by which an entity can be accessed, used, or interacted with.
-
C.
isOneOfPrimaryTimeZonesInAlaska
Indicates that a time zone is among the main officially used time zones within the state of Alaska.
-
D.
primaryAccessPoint
Indicates that one entity serves as the main or principal point through which another entity is accessed or entered.
-
E.
hasAnchorageArea
Indicates that one entity provides or defines an area suitable for anchoring (e.g., for vessels) in relation to 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_69e288c06a908190899cad4531f32c9a |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d9ca5a18819086da68b69eed8cc1 |
completed | April 29, 2026, 10:13 a.m. |
| PD | Predicate disambiguation | batch_69f1764345388190a3102b62ddb729b4 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:15 p.m.