Triple
T31714069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fellhorn/Kanzelwand ski area |
E809405
|
entity |
| Predicate | hasFamilyFriendlyAreas |
P91937
|
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: [Fellhorn/Kanzelwand ski area, hasFamilyFriendlyAreas, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFamilyFriendlyAreas Context triple: [Fellhorn/Kanzelwand ski area, hasFamilyFriendlyAreas, yes]
-
A.
hasKidFriendlyFeatures
Indicates that something possesses characteristics, amenities, or design elements that are suitable and appealing for children.
-
B.
hasRecreationalArea
Indicates that an entity includes, provides, or is associated with a designated space intended for leisure or recreational activities.
-
C.
hasFamilyArea
chosen
Indicates a relationship where an entity possesses or includes a designated area intended for family use or family-related activities.
-
D.
isRecreationalArea
Indicates that a place or space is designated and used primarily for leisure, relaxation, or recreational activities.
-
E.
isFamilyFriendly
Indicates that something is suitable for all ages and does not contain content inappropriate for children or sensitive audiences.
- 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_69f348df4e048190a4a5a9932ada78d6 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
Created at: April 30, 2026, 11:16 p.m.