Triple
T9839217
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vernal, Utah |
E239178
|
entity |
| Predicate | outdoorActivitiesAvailable |
P59252
|
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: [Vernal, Utah, outdoorActivitiesAvailable, hiking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: outdoorActivitiesAvailable Context triple: [Vernal, Utah, outdoorActivitiesAvailable, hiking]
-
A.
outdoorActivityType
chosen
Indicates the specific kind of outdoor activity associated with an entity or event.
-
B.
hasOutdoorResource
Indicates that an entity is associated with, provides, or includes access to an outdoor resource or facility.
-
C.
outdoorSection
Indicates that one entity is a section, area, or portion that is located outdoors or in an open-air environment relative to another entity.
-
D.
outdoorVenue
Indicates that an event, activity, or gathering takes place at a location situated outdoors rather than inside a building or enclosed structure.
-
E.
campCategory
Indicates the classification or type of camp to which an entity belongs (e.g., by purpose, style, or characteristics).
- 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_69ca84e3f0c48190ada72a65ebd50efd |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb34921b881909836ba0f5b42a27b |
completed | April 2, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cd03e30bc08190816c0a6d29c21b0f |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:33 p.m.