Triple
T30832913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Unzen |
E785271
|
entity |
| Predicate | 1792DisasterCause |
P145070
|
FINISHED |
| Object | flank collapse into Ariake Sea |
—
|
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: flank collapse into Ariake Sea | Statement: [Mount Unzen, 1792DisasterCause, flank collapse into Ariake Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 1792DisasterCause Context triple: [Mount Unzen, 1792DisasterCause, flank collapse into Ariake Sea]
-
A.
1792EruptionCaused
Indicates that one event or process was caused by the volcanic eruption that occurred in 1792.
-
B.
1792EruptionDeaths
Indicates that the referenced entities are connected through deaths caused by the volcanic eruption that occurred in the year 1792.
-
C.
causeOfDisaster
Indicates that the subject is responsible for bringing about or triggering the specified disaster.
-
D.
disasterCauseDetail
chosen
Indicates a detailed explanation of the specific cause or contributing factors behind a disaster.
-
E.
causeOf1956Disaster
Indicates that the subject is the factor, event, or agent responsible for causing the specific disaster that occurred in 1956.
- 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_69f224b73d8c81908129383bfb397c87 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6953bafb88190a860e9c68a3dd4b2 |
completed | May 3, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69f690ed5d008190831cf8e44cce28af |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 29, 2026, 8:44 p.m.