Triple
T13368003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grand Balcon Nord trail |
E318989
|
entity |
| Predicate | unsafeInConditions |
P84224
|
FINISHED |
| Object | heavy snow |
—
|
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: heavy snow | Statement: [Grand Balcon Nord trail, unsafeInConditions, heavy snow]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unsafeInConditions Context triple: [Grand Balcon Nord trail, unsafeInConditions, heavy snow]
-
A.
containsCondition
chosen
Indicates that one entity includes, embodies, or is associated with a particular condition.
-
B.
definesConditionsFor
Indicates that one entity specifies or establishes the rules, requirements, or circumstances under which another entity is valid, applicable, or operates.
-
C.
UNSafeArea
Indicates that a given area or region is considered dangerous, hazardous, or otherwise not safe for normal use or presence.
-
D.
hasSecurityConsideration
Indicates that there is a relevant security-related issue, risk, or precaution associated with the referenced entity.
-
E.
safetySetting
Indicates that an entity is configured with a particular safety-related parameter, mode, or constraint governing how it operates or behaves.
- 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_69d806b7bbac8190b85278c87fa7aff3 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dadcd652d48190a782fd1f57f34b6a |
completed | April 11, 2026, 11:44 p.m. |
| PD | Predicate disambiguation | batch_69d9a02c9abc8190b328e7bae747bfc5 |
completed | April 11, 2026, 1:13 a.m. |
Created at: April 9, 2026, 9:32 p.m.