Triple
T33815037
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Štěpánka observation tower |
E866648
|
entity |
| Predicate | hasTouristTrailAccess |
P167071
|
FINISHED |
| Object | marked hiking trails |
—
|
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: marked hiking trails | Statement: [Štěpánka observation tower, hasTouristTrailAccess, marked hiking trails]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTouristTrailAccess Context triple: [Štěpánka observation tower, hasTouristTrailAccess, marked hiking trails]
-
A.
hasTouristTrails
chosen
Indicates that an entity contains or is equipped with designated paths or routes intended for use by tourists.
-
B.
hasTouristRoute
Indicates that a location or site is connected to or included in a designated tourist route or itinerary.
-
C.
hasScenicAccessTo
Indicates that one place or object provides a visually appealing or notable view of another place or object.
-
D.
touristAccess
Indicates that a place or resource is available for use or visitation by tourists.
-
E.
hasTrailAccessPoint
Indicates that there is a specific access point or entrance connecting a location to a trail or pathway.
- 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_69f349911a8c81908478662194b23d8c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: May 1, 2026, 1:46 a.m.