Triple
T1269262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cascadia Subduction Zone |
E15671
|
entity |
| Predicate | paleoseismologyEvidenceFoundIn |
P22640
|
FINISHED |
| Object | coastal marshes |
—
|
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: coastal marshes | Statement: [Cascadia Subduction Zone, paleoseismologyEvidenceFoundIn, coastal marshes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: paleoseismologyEvidenceFoundIn Context triple: [Cascadia Subduction Zone, paleoseismologyEvidenceFoundIn, coastal marshes]
-
A.
hasGeologicalEvidenceOf
chosen
Indicates that there is geological data or features supporting the existence, occurrence, or impact of a specified phenomenon or event.
-
B.
tectonicEvents
Indicates the occurrence or involvement of entities in geological processes related to the movement and interaction of Earth’s tectonic plates, such as earthquakes, volcanic activity, or continental drift.
-
C.
earthquakeSequence
Indicates a relationship where multiple earthquakes are linked as part of the same temporal or causal sequence of seismic events.
-
D.
archaeologicalEvidenceAge
Indicates the age or time period to which a piece of archaeological evidence is dated.
-
E.
appliedElasticReboundTheoryTo
Indicates that one entity used the elastic rebound theory as a framework or method to analyze, explain, or solve something involving another 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_69a4935a94308190bb92555b79032824 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4c03aaa8c8190bacb7de5a38329da |
completed | March 1, 2026, 10:39 p.m. |
| PD | Predicate disambiguation | batch_69a4bede52a081909665d60acbe41d31 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:50 p.m.