Triple
T27291774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Bend State Park |
E688646
|
entity |
| Predicate | railTrailUse |
P156755
|
FINISHED |
| Object | hiking |
—
|
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: hiking | Statement: [North Bend State Park, railTrailUse, hiking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railTrailUse Context triple: [North Bend State Park, railTrailUse, hiking]
-
A.
trailUses
chosen
Indicates that a trail supports or is designated for specific types of use or activities (such as hiking, biking, or horseback riding).
-
B.
isRailTrail
Indicates that a path or route is a rail trail, meaning it follows or repurposes a former or existing railway corridor for recreational or transportation use.
-
C.
hasRailTrail
Indicates that one location or entity possesses, includes, or is connected by a rail trail (a recreational trail converted from or running along a former or existing railway corridor) to another location or entity.
-
D.
trailAccess
Indicates that one entity provides permission or a route for another entity to enter, use, or traverse a specific trail or pathway.
-
E.
bicycleUse
Indicates that an entity makes use of a bicycle for transportation, activity, or other purposes.
- 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_69ef355a96308190a2bed991525fb278 |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69f62759cb288190904e0b0531fea34d |
completed | May 2, 2026, 4:33 p.m. |
| PD | Predicate disambiguation | batch_69f620e38aec8190bb184edcdbd6da64 |
completed | May 2, 2026, 4:05 p.m. |
Created at: April 27, 2026, 11:16 a.m.