Triple

T2447786
Position Surface form Disambiguated ID Type / Status
Subject NVMe over Fabrics E53633 entity
Predicate transportIncludes P39916 FINISHED
Object RDMA
RDMA (Remote Direct Memory Access) is a high-performance networking technology that allows one computer to directly access the memory of another without involving the operating system or CPU, significantly reducing latency and CPU overhead in data transfers.
E268844 NE FINISHED

How this triple was built (5 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: RDMA | Statement: [NVMe over Fabrics, transportIncludes, RDMA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RDMA
Context triple: [NVMe over Fabrics, transportIncludes, RDMA]
  • A. InfiniBand
    InfiniBand is a high-speed, low-latency communications standard commonly used as the interconnect fabric in supercomputers and large-scale data centers.
  • B. NVMe over Fabrics
    NVMe over Fabrics is a network protocol that extends the high-performance NVMe storage interface across various network transports to enable low-latency, scalable access to remote solid-state storage.
  • C. Fibre Channel
    Fibre Channel is a high-speed network technology primarily used to connect computer data storage in storage area networks (SANs), offering low-latency, high-throughput communication for enterprise environments.
  • D. GPUDirect
    GPUDirect is an NVIDIA technology that enables high-speed, low-latency data transfers directly between GPUs and other devices or memory, bypassing the CPU to improve performance in data-intensive applications.
  • E. DMA
    DMA (Direct Memory Access) is a computer feature that allows hardware devices to transfer data directly to and from system memory without continuous CPU involvement, improving performance and efficiency.
  • 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: RDMA
Triple: [NVMe over Fabrics, transportIncludes, RDMA]
Generated description
RDMA (Remote Direct Memory Access) is a high-performance networking technology that allows one computer to directly access the memory of another without involving the operating system or CPU, significantly reducing latency and CPU overhead in data transfers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: RDMA
Target entity description: RDMA (Remote Direct Memory Access) is a high-performance networking technology that allows one computer to directly access the memory of another without involving the operating system or CPU, significantly reducing latency and CPU overhead in data transfers.
  • A. InfiniBand
    InfiniBand is a high-speed, low-latency communications standard commonly used as the interconnect fabric in supercomputers and large-scale data centers.
  • B. NVMe over Fabrics
    NVMe over Fabrics is a network protocol that extends the high-performance NVMe storage interface across various network transports to enable low-latency, scalable access to remote solid-state storage.
  • C. Fibre Channel
    Fibre Channel is a high-speed network technology primarily used to connect computer data storage in storage area networks (SANs), offering low-latency, high-throughput communication for enterprise environments.
  • D. GPUDirect
    GPUDirect is an NVIDIA technology that enables high-speed, low-latency data transfers directly between GPUs and other devices or memory, bypassing the CPU to improve performance in data-intensive applications.
  • E. DMA
    DMA (Direct Memory Access) is a computer feature that allows hardware devices to transfer data directly to and from system memory without continuous CPU involvement, improving performance and efficiency.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: transportIncludes
Context triple: [NVMe over Fabrics, transportIncludes, RDMA]
  • A. transports
    Indicates that one entity carries or conveys another entity from one place to another.
  • B. transportType
    Indicates the mode or means of transportation used in carrying something or someone from one place to another.
  • C. transportAssumption
    Indicates an assumption that something can be transported or carried from one place or context to another.
  • D. transportFor
    Indicates a relationship where one entity serves as the means or service used to move another entity from one place to another.
  • E. transportationFunction
    Indicates that one entity serves to move or carry another entity from one place to another.
  • F. None of above. chosen

Provenance (7 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_69ab495d227c8190b26ae6548eeb1019 completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd2bc7b5481908b3664495e99f1a4 completed March 7, 2026, 7:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69aef0c0069c8190bfb9e71aea4774d3 completed March 9, 2026, 4:09 p.m.
NEDg Description generation batch_69aef53740508190893b14bb1b411a30 completed March 9, 2026, 4:28 p.m.
NED2 Entity disambiguation (via description) batch_69aef9594024819088e7afc0e64429ff completed March 9, 2026, 4:46 p.m.
PD Predicate disambiguation batch_69abd0aed2688190a18fe66b98d80e0b completed March 7, 2026, 7:15 a.m.
PDg Predicate description generation batch_69abd2baee308190bdaa41ef1f6bc9cc completed March 7, 2026, 7:24 a.m.
Created at: March 6, 2026, 9:43 p.m.