Triple
T36488002
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | leapfrog integrator |
E898982
|
entity |
| Predicate | numericalErrorType |
P43799
|
FINISHED |
| Object | bounded energy error over long times |
—
|
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: bounded energy error over long times | Statement: [leapfrog integrator, numericalErrorType, bounded energy error over long times]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numericalErrorType Context triple: [leapfrog integrator, numericalErrorType, bounded energy error over long times]
-
A.
numericalStability
Indicates that a method, algorithm, or computation maintains reliable accuracy and bounded error growth under small input or rounding perturbations.
-
B.
numericType
Indicates that one entity specifies or constrains the kind or category of numeric value associated with another entity.
-
C.
errorType
chosen
Indicates the specific category or kind of error associated with an event, action, or entity.
-
D.
numericalProperty
Indicates that an entity is associated with a specific numeric value or measurable quantity.
-
E.
approximationType
Indicates the specific method or scheme used to approximate a value, function, or relationship in a given context.
- 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_69f76e5ad4588190bdbce60c52fbb785 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.