Triple
T22574419
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rivera microplate |
E544354
|
entity |
| Predicate | relativeMotionToCocosPlate |
P7348
|
FINISHED |
| Object | divergent |
—
|
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: divergent | Statement: [Rivera microplate, relativeMotionToCocosPlate, divergent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: relativeMotionToCocosPlate Context triple: [Rivera microplate, relativeMotionToCocosPlate, divergent]
-
A.
relativeMotionType
chosen
Indicates the type or nature of motion occurring between two entities relative to one another.
-
B.
relativePositionInSystem
Indicates the spatial or ordered position an entity occupies within a larger system or structured arrangement.
-
C.
relationshipToWorld
Indicates how an entity is connected or related to the broader world or external environment.
-
D.
movesRelativeTo
Indicates that one entity changes its position or orientation with respect to another entity, rather than with respect to a fixed reference frame.
-
E.
positionRelativeToSurface
Indicates how an entity is spatially located or oriented with respect to a reference surface.
- 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_69e11e30d05481909df915354c89f0d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f15fec296481908a6101b02e5bedaa |
completed | April 29, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69ee626e6bb08190ada4dd8b48cc0c43 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 16, 2026, 8:53 p.m.