Triple
T18723622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | extended Kalman filter |
E457842
|
entity |
| Predicate | linearizesAround |
P4460
|
FINISHED |
| Object | current state estimate |
—
|
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: current state estimate | Statement: [extended Kalman filter, linearizesAround, current state estimate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linearizesAround Context triple: [extended Kalman filter, linearizesAround, current state estimate]
-
A.
linearity
Indicates that a relationship between quantities preserves addition and scalar multiplication, so outputs change in direct proportion to inputs.
-
B.
approximates
chosen
Indicates that one entity is close to, but not exactly equal to, the value, form, or behavior of another entity.
-
C.
roundOf
Indicates that one event, match, or game occurs as a specific stage or phase within a larger competition or tournament.
-
D.
approximationRegion
Indicates a region or range within which a value, object, or condition is considered an acceptable approximation of a reference or target.
-
E.
isLinear
Indicates that a relationship, function, or structure preserves linearity, typically meaning it satisfies additivity and homogeneity (or forms a straight-line dependence between variables).
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56abcfc048190a01dee959e768768 |
completed | April 19, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:50 a.m.