Triple
T4990247
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Summit |
E112111
|
entity |
| Predicate | LINPACKPerformance |
P61344
|
FINISHED |
| Object | over 140 petaflops |
—
|
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: over 140 petaflops | Statement: [Summit, LINPACKPerformance, over 140 petaflops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: LINPACKPerformance Context triple: [Summit, LINPACKPerformance, over 140 petaflops]
-
A.
gpuComputePerformance
Indicates the level of processing capability a GPU can deliver for computational tasks, typically measured in operations per unit time.
-
B.
neuralEnginePerformance
Indicates the level or efficiency of processing capability provided by a neural engine in performing AI or machine-learning tasks.
-
C.
benchmarkFor
Indicates that one entity serves as a standard or reference point against which the performance, quality, or characteristics of another entity are measured or evaluated.
-
D.
performanceMeasurement
Indicates the act of assessing, quantifying, or evaluating how well an entity, process, or system performs against defined criteria or objectives.
-
E.
performanceCores
Indicates a relationship where certain cores within a processor are designated as high-performance cores optimized for speed and intensive tasks.
- F. None of above. chosen
Provenance (4 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_69bd441be7bc8190b530362d427b97d2 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd74249a8c8190952680aee06a9286 |
completed | March 20, 2026, 4:21 p.m. |
| PD | Predicate disambiguation | batch_69bd71492dec8190af4c27a3043b35cc |
completed | March 20, 2026, 4:09 p.m. |
| PDg | Predicate description generation | batch_69bd742311bc8190be016cac6cebd15d |
completed | March 20, 2026, 4:21 p.m. |
Created at: March 20, 2026, 1:34 p.m.