Triple
T15731826
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawaiian hotspot |
E381363
|
entity |
| Predicate | motionRelativeToPlate |
P7348
|
FINISHED |
| Object | nearly stationary |
—
|
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: nearly stationary | Statement: [Hawaiian hotspot, motionRelativeToPlate, nearly stationary]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motionRelativeToPlate Context triple: [Hawaiian hotspot, motionRelativeToPlate, nearly stationary]
-
A.
movesRelativeTo
Indicates that one entity changes its position or orientation with respect to another entity, rather than with respect to a fixed reference frame.
-
B.
correctorPlatePosition
Indicates the spatial placement or alignment of a corrector plate relative to the rest of the system.
-
C.
relativeMotionType
chosen
Indicates the type or nature of motion occurring between two entities relative to one another.
-
D.
motorPosition
Indicates the specific location or angle at which a motor’s moving component is currently set.
-
E.
positionInMovement
Indicates the specific role or placement an entity holds within a broader movement or collective action.
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fd3614481908b2694b1d3550058 |
completed | April 16, 2026, 2:56 a.m. |
| PD | Predicate disambiguation | batch_69e00526759c819088b80d85138b8974 |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:46 a.m.