Triple
T18021414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBN Butterfly parallel computer |
E431124
|
entity |
| Predicate | instanceOf |
P0
|
FINISHED |
| Object | massively parallel processing system |
C12874
|
CONCEPT FINISHED |
How this triple was built (1 step)
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.
CD
Concept disambiguation
gpt-5-mini-2025-08-07
Target class: massively parallel processing system Context triple: [BBN Butterfly parallel computer, instanceOf, massively parallel processing system]
-
A.
high-performance computing system
chosen
A high-performance computing system is an integrated collection of powerful processors, high-speed interconnects, and optimized software designed to perform large-scale, complex computations at very high speeds.
-
B.
petascale supercomputer
A petascale supercomputer is a massively parallel high-performance computing system capable of performing at least one quadrillion (10^15) floating-point operations per second, used for large-scale scientific, engineering, and data-intensive simulations.
-
C.
parallel computer bus
A parallel computer bus is a communication system that transfers multiple bits of data simultaneously across multiple wires or channels between components within a computer system.
-
D.
mainframe computer
A mainframe computer is a large, powerful, and highly reliable central computer system designed to process vast amounts of data and support numerous simultaneous users and critical applications, typically used by large organizations.
-
E.
global data-processing and forecasting system
A global data-processing and forecasting system is an integrated platform that ingests, cleans, analyzes, and models large-scale, heterogeneous data from worldwide sources to generate timely predictions and insights for decision-making.
- F. None of above.
Provenance (1 batch)
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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
Created at: April 10, 2026, 10:24 a.m.