Triple
T9796221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oruanui eruption of Taupō volcano |
E237723
|
entity |
| Predicate | depositThickness |
P9690
|
FINISHED |
| Object | ignimbrite locally more than 200 metres thick |
—
|
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: ignimbrite locally more than 200 metres thick | Statement: [Oruanui eruption of Taupō volcano, depositThickness, ignimbrite locally more than 200 metres thick]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: depositThickness Context triple: [Oruanui eruption of Taupō volcano, depositThickness, ignimbrite locally more than 200 metres thick]
-
A.
thickness
chosen
Indicates the measure of how deep or wide an object or layer is from one surface or side to its opposite.
-
B.
depositType
Indicates the specific kind or category of deposit associated with an account, transaction, or financial arrangement.
-
C.
depositary
Indicates that one entity holds or safeguards something (such as assets, documents, or funds) on behalf of another entity.
-
D.
deposited
Indicates that an entity has placed or put something into another entity, typically transferring it into a container, location, or account.
-
E.
depthMetresApprox
Indicates an approximate measurement of how deep something is in metres, rather than an exact value.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda34a53548190a8cb524381fe2bf9 |
completed | April 1, 2026, 10:59 p.m. |
| PD | Predicate disambiguation | batch_69cd03da45a88190b71b1be3354c15a6 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:28 p.m.