Triple
T30971111
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glacier Spur Road |
E789099
|
entity |
| Predicate | terminusLeadsTo |
P167776
|
FINISHED |
| Object | Mendenhall Glacier Recreation Area |
—
|
NE NERFINISHED |
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: Mendenhall Glacier Recreation Area | Statement: [Glacier Spur Road, terminusLeadsTo, Mendenhall Glacier Recreation Area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: terminusLeadsTo Context triple: [Glacier Spur Road, terminusLeadsTo, Mendenhall Glacier Recreation Area]
-
A.
terminusTowards
Indicates that one entity serves as the endpoint or directional terminus oriented toward another entity.
-
B.
terminus
Indicates that one entity serves as the final endpoint or stopping place for another entity’s movement, route, or process.
-
C.
terminusConnectsTo
chosen
Indicates that a transportation route’s endpoint is directly linked or transitions to another route, line, or terminal.
-
D.
terminusFrom
Indicates that something serves as the endpoint or final destination from which a route, path, or connection originates.
-
E.
terminusFeature
Indicates that a specific physical or structural feature is located at, marks, or characterizes the endpoint or terminus of something.
- 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_69f224c3a6b48190951add9b7b7f0271 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f71996e1a48190ac59a1d66d7c44e8 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71820c6c88190ab38b4fa626d22cc |
completed | May 3, 2026, 9:40 a.m. |
Created at: April 29, 2026, 8:54 p.m.