Triple
T37438820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sólheimajökull |
E930352
|
entity |
| Predicate | hazardSource |
P187818
|
FINISHED |
| Object | subglacial volcanic activity of Katla |
—
|
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: subglacial volcanic activity of Katla | Statement: [Sólheimajökull, hazardSource, subglacial volcanic activity of Katla]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hazardSource Context triple: [Sólheimajökull, hazardSource, subglacial volcanic activity of Katla]
-
A.
hazardType
Indicates the specific kind or category of hazard associated with an entity or situation.
-
B.
hazardScope
Indicates the range or extent within which a particular hazard is relevant, applicable, or has effect.
-
C.
hazardEvent
Indicates an occurrence of a dangerous or harmful event that poses a risk or threat within a given context.
-
D.
isHazard
Indicates that something poses a potential risk, danger, or harmful condition to people, property, or the environment.
-
E.
hazardChainElement
Indicates that one hazard is a component, step, or link within a larger sequence or chain of related hazardous events or conditions.
- F. None of above. chosen
Provenance (4 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_69f76ebfdcb8819098562ff3db673b04 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb92efc5948190a040ba2028bab964 |
completed | May 6, 2026, 7:13 p.m. |
| PD | Predicate disambiguation | batch_69fb8d0b52588190bb29937a43b99b5e |
completed | May 6, 2026, 6:48 p.m. |
| PDg | Predicate description generation | batch_69fb92ee27408190b0116ef2d789abac |
completed | May 6, 2026, 7:13 p.m. |
Created at: May 3, 2026, 4:17 p.m.