Triple
T737775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | von Neumann architecture |
E14971
|
entity |
| Predicate | characterizedBy |
P662
|
FINISHED |
| Object |
von Neumann bottleneck
The von Neumann bottleneck is a performance limitation in traditional computer designs where a single shared path for instructions and data between the CPU and memory creates a throughput constraint.
|
E14971
|
NE FINISHED |
How this triple was built (4 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: von Neumann bottleneck | Statement: [von Neumann architecture, characterizedBy, von Neumann bottleneck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: von Neumann bottleneck Context triple: [von Neumann architecture, characterizedBy, von Neumann bottleneck]
-
A.
von Neumann architecture
The von Neumann architecture is a foundational computer design model in which a single memory stores both program instructions and data, executed sequentially by a central processing unit.
-
B.
Moore's law
Moore's law is an observation and prediction that the number of transistors on an integrated circuit—and thus computing power—tends to roughly double at regular intervals, driving exponential growth in digital technology.
-
C.
“Cramming more components onto integrated circuits”
“Cramming more components onto integrated circuits” is the landmark 1965 article by Gordon E. Moore that introduced the observation later known as Moore’s Law, predicting the exponential growth of transistor density on integrated circuits.
-
D.
Turing machine
A Turing machine is an abstract computational model that manipulates symbols on an infinite tape according to a set of rules, providing a formal foundation for the concept of algorithm and computability.
-
E.
Monolithic Memories
Monolithic Memories was a semiconductor company known for developing programmable read-only memory (PROM) and logic devices after being spun off from Fairchild Semiconductor.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: von Neumann bottleneck Triple: [von Neumann architecture, characterizedBy, von Neumann bottleneck]
Generated description
The von Neumann bottleneck is a performance limitation in traditional computer designs where a single shared path for instructions and data between the CPU and memory creates a throughput constraint.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: von Neumann bottleneck Target entity description: The von Neumann bottleneck is a performance limitation in traditional computer designs where a single shared path for instructions and data between the CPU and memory creates a throughput constraint.
-
A.
von Neumann architecture
chosen
The von Neumann architecture is a foundational computer design model in which a single memory stores both program instructions and data, executed sequentially by a central processing unit.
-
B.
Moore's law
Moore's law is an observation and prediction that the number of transistors on an integrated circuit—and thus computing power—tends to roughly double at regular intervals, driving exponential growth in digital technology.
-
C.
“Cramming more components onto integrated circuits”
“Cramming more components onto integrated circuits” is the landmark 1965 article by Gordon E. Moore that introduced the observation later known as Moore’s Law, predicting the exponential growth of transistor density on integrated circuits.
-
D.
Turing machine
A Turing machine is an abstract computational model that manipulates symbols on an infinite tape according to a set of rules, providing a formal foundation for the concept of algorithm and computability.
-
E.
Monolithic Memories
Monolithic Memories was a semiconductor company known for developing programmable read-only memory (PROM) and logic devices after being spun off from Fairchild Semiconductor.
- F. None of above.
Provenance (5 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_69a4934d9930819099eed80096b0597d |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5effc108190aea8fbe86641ba54 |
completed | March 1, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a64a618c248190ab1bcecba04d3da8 |
completed | March 3, 2026, 2:41 a.m. |
| NEDg | Description generation | batch_69a64b4c8bb88190aa413a4bed256129 |
completed | March 3, 2026, 2:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a64beaafa0819099b02cca0f6c79b7 |
completed | March 3, 2026, 2:48 a.m. |
Created at: March 1, 2026, 7:37 p.m.