Triple
T13077045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vulcanian eruption |
E329604
|
entity |
| Predicate | tephraGrainSize |
P12318
|
FINISHED |
| Object | fine ash to blocks |
—
|
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: fine ash to blocks | Statement: [Vulcanian eruption, tephraGrainSize, fine ash to blocks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tephraGrainSize Context triple: [Vulcanian eruption, tephraGrainSize, fine ash to blocks]
-
A.
tephraVolume
Indicates the amount of volcanic tephra produced or present, typically expressed as a measurable volume.
-
B.
tephraName
Indicates that one entity is the designated name or label assigned to a specific tephra (volcanic ash or pyroclastic) unit.
-
C.
typicalSedimentSizeRange
Indicates the usual range of sediment particle sizes associated with an entity or environment.
-
D.
grainSize
chosen
Indicates the relative coarseness or fineness of the material or particles involved in the relationship.
-
E.
tephraFallCoverage
Indicates the spatial extent or area over which volcanic tephra (ash and debris) has been deposited or is expected to fall.
- 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_69d80771749c81909a6d9197b9504872 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69d9811828448190ac6ddd3e9c221251 |
completed | April 10, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69d9803d46688190bac6b7d208f08d01 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:01 p.m.