Triple
T2145336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke Gardens |
E47050
|
entity |
| Predicate | hasWalkingTrails |
P17835
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Duke Gardens, hasWalkingTrails, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWalkingTrails Context triple: [Duke Gardens, hasWalkingTrails, yes]
-
A.
hasRecreationalRoute
chosen
Indicates that an entity is associated with or includes a route intended for recreational activities such as walking, cycling, or hiking.
-
B.
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.
-
C.
hasTowpath
Indicates that a waterway or canal is accompanied by a path running alongside it, typically used for towing boats.
-
D.
hasHikingTrailToTop
Indicates that there exists a hiking trail leading from a starting location to the top or summit of a specified destination.
-
E.
TrailLinkIs
Indicates that one trail segment is connected to or continues from another trail segment.
- 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_69a88a1933e0819094f18426ed74180f |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbeaa14bc81908486683decd7ae42 |
completed | March 7, 2026, 5:59 a.m. |
| PD | Predicate disambiguation | batch_69abbd9846e88190b6c2941dd9ce7749 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:44 p.m.