Triple
T12597485
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | classical fourth-order Runge–Kutta method |
E300768
|
entity |
| Predicate | usesTimeStepping |
P52987
|
FINISHED |
| Object | discrete grid t_n = t_0 + n h |
—
|
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: discrete grid t_n = t_0 + n h | Statement: [classical fourth-order Runge–Kutta method, usesTimeStepping, discrete grid t_n = t_0 + n h]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTimeStepping Context triple: [classical fourth-order Runge–Kutta method, usesTimeStepping, discrete grid t_n = t_0 + n h]
-
A.
timeSteppingDirection
Indicates the direction in which time progresses or is advanced within a process, simulation, or sequence of steps.
-
B.
timeOfIntegration
Indicates the specific point or period in time when one entity is incorporated, combined, or merged into another system, process, or structure.
-
C.
timeDiscretization
Indicates how a continuous or overall time period is divided into discrete intervals or steps for representation or processing.
-
D.
timeDependence
Indicates that one entity’s state, value, or behavior is determined by or varies as a function of another entity over time.
-
E.
timeDiscretizationFormula
chosen
Indicates a relationship where a specific mathematical formula is used to convert or approximate continuous time into discrete time steps for analysis or computation.
- 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9559458dc8190bc4d6e697e99d70e |
completed | April 10, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69d9541894fc8190a0c3706a414279f0 |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 9, 2026, 5:08 p.m.