Triple
T6232665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Pelée |
E139392
|
entity |
| Predicate | eruption1902Effect |
P53970
|
FINISHED |
| Object | destruction of Saint-Pierre |
—
|
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: destruction of Saint-Pierre | Statement: [Mount Pelée, eruption1902Effect, destruction of Saint-Pierre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eruption1902Effect Context triple: [Mount Pelée, eruption1902Effect, destruction of Saint-Pierre]
-
A.
eruptionEffect
Indicates the impact or consequences that an eruption has on its surrounding environment, systems, or entities.
-
B.
eruptionImpact
chosen
Indicates the effects or consequences that a volcanic eruption has on surrounding entities, environments, or systems.
-
C.
eruptionSeriesOf
Indicates a relationship where a specific volcanic eruption is a member event within a broader series or sequence of related eruptions.
-
D.
eruptionName
Indicates the specific name assigned to a volcanic eruption event associated with an entity.
-
E.
erupted
Indicates that a volcano or similar geological feature suddenly expelled lava, ash, gas, or other material in a violent outburst.
- 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_69c008b0e7ac8190808a59573ee646f3 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c062ee6f088190bf72692eb8ffb761 |
completed | March 22, 2026, 9:45 p.m. |
| PD | Predicate disambiguation | batch_69c05601de6481909d0880048fd7b49a |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:22 p.m.