Triple
T3501240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Waters |
E73972
|
entity |
| Predicate | peakPerformance |
P23737
|
FINISHED |
| Object | over 1 petaflop |
—
|
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 1 petaflop | Statement: [Blue Waters, peakPerformance, over 1 petaflop]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: peakPerformance Context triple: [Blue Waters, peakPerformance, over 1 petaflop]
-
A.
performanceFocus
Indicates that an entity directs attention or effort toward improving or emphasizing performance in a given context.
-
B.
performance
chosen
Indicates that one entity’s effectiveness, quality, or success in carrying out a task, function, or role is being evaluated or characterized in relation to some standard or expectation.
-
C.
performanceTuningBy
Indicates that an entity’s performance has been adjusted, optimized, or fine-tuned by another entity.
-
D.
performancePackage
Indicates that an entity is associated with a specific performance-related bundle or configuration, typically grouping features or enhancements that affect its performance.
-
E.
impactOnPerformance
Indicates that one entity has an effect, influence, or consequence on the performance level or effectiveness of another entity.
- 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_69ad85cdb6e48190a335d412b9194ed8 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbbd5fbe8819091b61fa8df355f0c |
completed | March 8, 2026, 6:11 p.m. |
| PD | Predicate disambiguation | batch_69adae0cd8b0819099da300af09880da |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.