Triple
T21492351
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2016 Kaikōura earthquake |
E530267
|
entity |
| Predicate | causedGroundDeformation |
P13016
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [2016 Kaikōura earthquake, causedGroundDeformation, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: causedGroundDeformation Context triple: [2016 Kaikōura earthquake, causedGroundDeformation, true]
-
A.
triggeredLandslides
Indicates that one entity caused or initiated landslides affecting another entity or area.
-
B.
seismicityCause
Indicates that one factor or event is the cause or source of observed seismic activity in another context or location.
-
C.
causesGeologicalProcess
chosen
Indicates that one entity brings about, initiates, or is responsible for a geological process occurring in another or in the environment.
-
D.
deformationEvents
Indicates that one or more deformation-related events (such as changes in shape, structure, or integrity) occur to or are associated with the referenced entity.
-
E.
geologicalIssue
Indicates a relationship where something is affected by, involves, or is characterized as a geological problem, hazard, or concern.
- 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_69e0c45bd15481909fba5910765cdda2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9ea3ba2fc81909638bbb3e1d92ea5 |
completed | April 23, 2026, 9:45 a.m. |
| PD | Predicate disambiguation | batch_69e631f6e68081908f5ee4ce7413803e |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:23 p.m.