Triple
T18212714
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Starý Smokovec |
E436072
|
entity |
| Predicate | touristTrailheadFor |
P62103
|
FINISHED |
| Object | hiking routes to Hrebienok |
—
|
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 routes to Hrebienok | Statement: [Starý Smokovec, touristTrailheadFor, hiking routes to Hrebienok]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: touristTrailheadFor Context triple: [Starý Smokovec, touristTrailheadFor, hiking routes to Hrebienok]
-
A.
hasTrailheads
chosen
Indicates that one location or area contains or provides access points where trails begin.
-
B.
tourStaple
Indicates that something is a standard, frequently included element or highlight of a tour.
-
C.
showsTrails
Indicates that one entity visually displays or renders the trails or paths associated with another entity.
-
D.
trailblazerFor
Indicates that one entity serves as a pioneering example, opening the way or setting a precedent for another entity to follow or build upon.
-
E.
tourDocumented
Indicates that a tour has been recorded or documented, typically capturing its details, events, or progression.
- 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_69d8b90dba6481908e119eb9aa4ca0cb |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4e22a26308190a6720b41a9bbfc2d |
completed | April 19, 2026, 2:09 p.m. |
| PD | Predicate disambiguation | batch_69e4332155d88190b106d0dceb4554af |
completed | April 19, 2026, 1:42 a.m. |
Created at: April 10, 2026, 10:32 a.m.