Triple
T36082141
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regenstein Castle |
E1043677
|
entity |
| Predicate | hasNearbyTrails |
P12052
|
FINISHED |
| Object | hiking paths in Harz region |
—
|
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 paths in Harz region | Statement: [Regenstein Castle, hasNearbyTrails, hiking paths in Harz region]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyTrails Context triple: [Regenstein Castle, hasNearbyTrails, hiking paths in Harz region]
-
A.
hasNearbyTrail
chosen
Indicates that one entity is located close to or within a short distance of a trail.
-
B.
hasNearbyTrailheadFor
Indicates that one location has a trailhead situated close enough to serve as a convenient access point for another location.
-
C.
hasNearbyTrailFeature
Indicates that one entity has another entity as a trail-related feature located in close physical proximity.
-
D.
hasNearbyTrailType
Indicates that one entity has another entity of a specified trail type located in close proximity to it.
-
E.
hikingTrailPassesNear
Indicates that a hiking trail runs close to, but does not directly intersect or pass through, a specified location or feature.
- 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_69f76e3154908190a6f702671c2bea08 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a0049e40d60819081e3899d8d9fca51 |
completed | May 10, 2026, 9:03 a.m. |
| PD | Predicate disambiguation | batch_6a0048c47b548190ad31b2901cc3784a |
completed | May 10, 2026, 8:58 a.m. |
Created at: May 3, 2026, 4:08 p.m.