Triple
T10067909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | POWER2 |
E213144
|
entity |
| Predicate | floatingPointPrecision |
P6941
|
FINISHED |
| Object | single precision |
—
|
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: single precision | Statement: [POWER2, floatingPointPrecision, single precision]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: floatingPointPrecision Context triple: [POWER2, floatingPointPrecision, single precision]
-
A.
floatingPointPerformance
Indicates the level of computational capability or efficiency an entity has when performing floating-point arithmetic operations.
-
B.
numericalStability
Indicates that a method, algorithm, or computation maintains reliable accuracy and bounded error growth under small input or rounding perturbations.
-
C.
floatType
chosen
Indicates that an entity has a specific floating-point data type or is categorized as a floating-point numeric value.
-
D.
supportsPrecisionLevels
Indicates that one entity is capable of operating at, or accommodating, multiple specified levels of precision in relation to another entity or process.
-
E.
floatingPointRegisterCount
Indicates the number of floating-point registers associated with an entity (such as a processor or execution 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_69ca83977128819084084eb7d1d8c52a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcff798bc8190a84af7bedea66f0a |
completed | April 2, 2026, 2:09 a.m. |
| PD | Predicate disambiguation | batch_69cd4b92573481909389bc6148ae7ea8 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 8:58 p.m.