Triple
T32158215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taupō volcano |
E821354
|
entity |
| Predicate | calderaFilledBy |
P173646
|
FINISHED |
| Object | Lake Taupō |
E90277
|
NE 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: Lake Taupō | Statement: [Taupō volcano, calderaFilledBy, Lake Taupō]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: calderaFilledBy Context triple: [Taupō volcano, calderaFilledBy, Lake Taupō]
-
A.
calderaStructure
Indicates a structural or morphological relationship in which one geological feature forms, defines, or contributes to the caldera configuration of another.
-
B.
calderaName
Indicates that an entity is assigned the proper name of a caldera.
-
C.
locatedInCalderaOf
Indicates that one entity is situated within the caldera (the large volcanic crater) of another entity.
-
D.
calderaState
Indicates the current condition or status of a volcanic caldera, such as whether it is active, dormant, stable, or undergoing change.
-
E.
calderaDepth
Indicates the vertical distance from a caldera’s rim down to its lowest interior point.
- F. None of above. chosen
Provenance (5 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2f46bece588190b74565620650c175 |
completed | June 15, 2026, 12:26 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a970b0819090c6473844ffa8e3 |
completed | May 3, 2026, 2:32 a.m. |
| PDg | Predicate description generation | batch_69f6b49339048190b617a6749f648825 |
completed | May 3, 2026, 2:36 a.m. |
Created at: May 1, 2026, 12:32 a.m.