Triple
T32495698
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Echinus Geyser |
E830516
|
entity |
| Predicate | hasEruptionInterval |
P12664
|
FINISHED |
| Object | highly variable |
—
|
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: highly variable | Statement: [Echinus Geyser, hasEruptionInterval, highly variable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEruptionInterval Context triple: [Echinus Geyser, hasEruptionInterval, highly variable]
-
A.
hasEruptionEpisodes
Indicates that an entity (such as a volcano or geyser) undergoes one or more distinct eruption events over time.
-
B.
eruptionFrequency
chosen
Indicates how often an eruption event occurs within a given time period.
-
C.
hasFrequentEruptionsSince
Indicates that an entity has experienced eruptions repeatedly and at relatively short intervals starting from a specified point in time.
-
D.
eruptionPotential
Indicates the likelihood or capacity of something (typically a volcano or similar system) to erupt under given conditions.
-
E.
hasEruptionVolume
Indicates the relationship between a volcanic eruption event and the measured volume of material it releases.
- 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_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 12:59 a.m.