Triple
T32158232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taupō volcano |
E821354
|
entity |
| Predicate | ŌruanuiEruptionAge |
P34963
|
FINISHED |
| Object | about 25,400 years ago |
—
|
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: about 25,400 years ago | Statement: [Taupō volcano, ŌruanuiEruptionAge, about 25,400 years ago]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ŌruanuiEruptionAge Context triple: [Taupō volcano, ŌruanuiEruptionAge, about 25,400 years ago]
-
A.
notableEruptionAge
chosen
Indicates the age or time period at which a notable volcanic eruption associated with an entity occurred.
-
B.
lastEruptionApproximateDate
Indicates that the recorded date of the most recent eruption is an estimate rather than an exact, precisely known date.
-
C.
eruptionObserved
Indicates that an eruption event has been witnessed, detected, or recorded by an observer or observing system.
-
D.
eruptionPeakDate
Indicates the specific date on which an eruption reaches its maximum intensity or peak activity.
-
E.
lastEruption
Indicates the time or event corresponding to the most recent eruption associated with a given entity.
- 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_69f34905e098819082191a6922a6d607 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6ba1733408190af579d93a7946508 |
completed | May 3, 2026, 2:59 a.m. |
| PD | Predicate disambiguation | batch_69f6b6293188819080d5041ca0adb969 |
completed | May 3, 2026, 2:42 a.m. |
Created at: May 1, 2026, 12:32 a.m.