Triple
T4203259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sakurajima |
E86119
|
entity |
| Predicate | hasLava |
P15890
|
FINISHED |
| Object | andesitic composition |
—
|
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: andesitic composition | Statement: [Sakurajima, hasLava, andesitic composition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLava Context triple: [Sakurajima, hasLava, andesitic composition]
-
A.
hasLavaFlow
Indicates that one entity exhibits, contains, or is associated with a flow of lava originating from volcanic activity.
-
B.
hasFumaroles
Indicates the presence of fumaroles (openings emitting volcanic gases or steam) associated with an entity.
-
C.
hasLavaDomes
Indicates that the subject volcano possesses one or more lava domes as part of its structure or eruptive features.
-
D.
hasVolcano
Indicates that one entity possesses, contains, or is the location of a volcano.
-
E.
typicalLavaType
chosen
Indicates the usual or characteristic type of lava associated with a given volcanic feature, eruption, or context.
- 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0380d470819091ffdb1161437266 |
completed | March 9, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69af01959c4881909eb1adcb3bdadbe6 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:49 p.m.