Triple
T14597408
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sete Cidades |
E342606
|
entity |
| Predicate | hasTypeOfVolcano |
P80402
|
FINISHED |
| Object | stratovolcano caldera |
—
|
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: stratovolcano caldera | Statement: [Sete Cidades, hasTypeOfVolcano, stratovolcano caldera]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfVolcano Context triple: [Sete Cidades, hasTypeOfVolcano, stratovolcano caldera]
-
A.
isTypeOfVolcano
chosen
Indicates that one entity is classified as a specific type or category of volcano in relation to another entity.
-
B.
containsVolcanoType
Indicates that a geographic area or feature includes at least one volcano of the specified type.
-
C.
hasVolcano
Indicates that one entity possesses, contains, or is the location of a volcano.
-
D.
isVolcanic
Indicates that something is characterized by or related to volcanic activity, such as originating from, produced by, or associated with a volcano.
-
E.
isExplosiveVolcano
Indicates that a volcano is currently or typically capable of explosive eruptions, characterized by violent release of gas, ash, and pyroclastic material.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb436d92881908fdf9267568feee2 |
completed | April 14, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:25 a.m.