Triple
T29130421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bend Parkway |
E738358
|
entity |
| Predicate | hasThroughRoute |
P4374
|
FINISHED |
| Object | U.S. Route 97 |
—
|
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: U.S. Route 97 | Statement: [Bend Parkway, hasThroughRoute, U.S. Route 97]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasThroughRoute Context triple: [Bend Parkway, hasThroughRoute, U.S. Route 97]
-
A.
hasRoute
chosen
Indicates that there exists a path or connection enabling travel or communication from one entity to another.
-
B.
hasAlongRoute
Indicates that one entity lies on or is situated along the path, course, or route taken by another entity.
-
C.
hasCommonRoute
Indicates that two or more entities share at least one overlapping or identical route or path.
-
D.
hasRouteConsideration
Indicates that one entity takes another entity into account when planning, evaluating, or determining a route.
-
E.
hasThroughServiceWith
Indicates that two transportation services are operationally linked so that a passenger or shipment can continue from one to the other without a separate booking or major interruption.
- 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_69f07cb29cdc8190afa55444553de60c |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f69383222c81909d8baa04129d5c81 |
completed | May 3, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 28, 2026, 11:31 a.m.