Triple
T35326936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crater Peak |
E1020211
|
entity |
| Predicate | ashCloudHazardTo |
P138581
|
FINISHED |
| Object | North Pacific air routes |
—
|
NE NERFINISHED |
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: North Pacific air routes | Statement: [Crater Peak, ashCloudHazardTo, North Pacific air routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ashCloudHazardTo Context triple: [Crater Peak, ashCloudHazardTo, North Pacific air routes]
-
A.
hazardEvent
Indicates an occurrence of a dangerous or harmful event that poses a risk or threat within a given context.
-
B.
naturalHazardFunction
chosen
Indicates a functional relationship where an entity serves as, causes, or performs the role of a natural hazard (e.g., earthquake, flood, storm) affecting other entities or environments.
-
C.
hazardType
Indicates the specific kind or category of hazard associated with an entity or situation.
-
D.
geologicalHazardZoneFor
Indicates a relationship where a specified area or zone is identified as being at risk from a particular geological hazard (such as earthquakes, landslides, or volcanic activity).
-
E.
geologicHazardLevel
Indicates the degree of potential danger or risk posed by geologic processes or conditions at a given location.
- 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_69f76deacf4481908e7735a5a7715b0a |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69f79533b88c8190934ec4cb21770e24 |
completed | May 3, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69f79104f5b48190a496cdffde8472da |
completed | May 3, 2026, 6:16 p.m. |
Created at: May 3, 2026, 4:03 p.m.