Triple
T32495696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Echinus Geyser |
E830516
|
entity |
| Predicate | hasEruptionColumnHeight |
P37156
|
FINISHED |
| Object | up to several meters |
—
|
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: up to several meters | Statement: [Echinus Geyser, hasEruptionColumnHeight, up to several meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEruptionColumnHeight Context triple: [Echinus Geyser, hasEruptionColumnHeight, up to several meters]
-
A.
eruptionHeight
chosen
Indicates the vertical distance or altitude reached by an eruption from its source.
-
B.
hasEruptionVolume
Indicates the relationship between a volcanic eruption event and the measured volume of material it releases.
-
C.
eruptionColumnPotential
Indicates the potential height or intensity of the column of material ejected into the atmosphere during an eruption.
-
D.
eruptionColumnType
Indicates the type or classification of the column of material (ash, gas, tephra) produced during a volcanic eruption.
-
E.
GreatEruptionPeakMagnitude
Indicates the peak intensity or maximum magnitude reached during a Great Eruption event.
- 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_69f349219cb8819087e120f509629c1b |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c40e16d0819084ab23950b416eb6 |
completed | May 3, 2026, 3:42 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: May 1, 2026, 12:59 a.m.