Triple
T17441600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Okehampton railway station |
E424666
|
entity |
| Predicate | hasFootpathAccessTo |
P25669
|
FINISHED |
| Object | Dartmoor walking routes |
—
|
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: Dartmoor walking routes | Statement: [Okehampton railway station, hasFootpathAccessTo, Dartmoor walking routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFootpathAccessTo Context triple: [Okehampton railway station, hasFootpathAccessTo, Dartmoor walking routes]
-
A.
hasPedestrianAccessTo
chosen
Indicates that a location or area can be reached or entered safely and directly by people on foot.
-
B.
hasNoDirectRoadAccess
Indicates that there is no direct road connection available between the relevant locations or entities.
-
C.
isRoadAccessible
Indicates that a road can be safely and legally used or traversed under the current conditions.
-
D.
hasFootways
Indicates that something includes or is connected to designated footpaths or pedestrian walkways.
-
E.
hasSeparateAccessRoadFor
Indicates that one entity is served by its own distinct access road that is separate from the access road used by 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44ff75538819083f77756d39a1aaa |
completed | April 19, 2026, 3:45 a.m. |
| PD | Predicate disambiguation | batch_69e3b030eac481909b8402719cc3102e |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:46 a.m.