Triple
T1007999
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawaiian–Emperor seamount chain |
E21756
|
entity |
| Predicate | volcanicRockType |
P15890
|
FINISHED |
| Object | basalt |
—
|
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: basalt | Statement: [Hawaiian–Emperor seamount chain, volcanicRockType, basalt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: volcanicRockType Context triple: [Hawaiian–Emperor seamount chain, volcanicRockType, basalt]
-
A.
volcanismType
Indicates the specific kind or style of volcanic activity or processes associated with an entity.
-
B.
typeOfVolcanicFeature
Indicates that one entity is classified as a specific kind or category of volcanic feature represented by the other entity.
-
C.
typicalLavaType
chosen
Indicates the usual or characteristic type of lava associated with a given volcanic feature, eruption, or context.
-
D.
volcanicOrigin
Indicates that something originates from, is produced by, or is directly associated with volcanic activity or processes.
-
E.
craterLakeType
Indicates that the subject is a lake formed in or associated with a volcanic crater, specifying this particular type of lake.
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b7f4c66c8190b6098fb72c1465a3 |
completed | March 1, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69a4b7203124819091de68cba5f731c1 |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:41 p.m.