Triple
T30405129
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IBM Roadrunner |
E773457
|
entity |
| Predicate | sustainedPerformance |
P169170
|
FINISHED |
| Object | 1.026 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: 1.026 petaflops | Statement: [IBM Roadrunner, sustainedPerformance, 1.026 petaflops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sustainedPerformance Context triple: [IBM Roadrunner, sustainedPerformance, 1.026 petaflops]
-
A.
sustainedBy
Indicates that one entity is maintained, supported, or kept in existence by another entity over a period of time.
-
B.
performanceAs
Indicates that one entity serves in a particular role, character, or capacity within a performance or presentation involving another entity.
-
C.
performanceWith
Indicates a relationship where two or more entities participate together in the same performance or staged presentation.
-
D.
performsWellOn
Indicates that one entity achieves good results or high performance when evaluated using, or operating within, another entity (such as a task, test, or environment).
-
E.
performanceBasis
Indicates that one entity’s performance is evaluated, determined, or justified on the basis of another specified factor, standard, or reference.
- 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_69f2248facd48190b183c3f3ca6daef7 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6861d69a08190802564e3aa7d6ea7 |
completed | May 2, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f679496c188190ba585792f987a1f4 |
completed | May 2, 2026, 10:23 p.m. |
Created at: April 29, 2026, 8:03 p.m.