Triple
T20399942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IP over InfiniBand |
E500303
|
entity |
| Predicate | relatedTo |
P37
|
FINISHED |
| Object | RDMA over InfiniBand |
—
|
NE NERFINISHED |
How this triple was built (3 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 over InfiniBand | Statement: [IP over InfiniBand, relatedTo, RDMA over InfiniBand]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RDMA over InfiniBand Context triple: [IP over InfiniBand, relatedTo, RDMA over InfiniBand]
-
A.
RDMA over Converged Ethernet
RDMA over Converged Ethernet is a network protocol that enables Remote Direct Memory Access over Ethernet networks to provide low-latency, high-throughput data transfer commonly used in high-performance computing and data centers.
-
B.
RDMA over TCP/IP
RDMA over TCP/IP is a networking technology that provides remote direct memory access capabilities over standard TCP/IP networks, enabling low-latency, high-throughput data transfer without involving the host CPU.
-
C.
IP over InfiniBand
IP over InfiniBand is a networking technology that enables standard Internet Protocol (IP) traffic to run over high-speed InfiniBand fabrics, allowing IP-based applications to leverage InfiniBand’s low latency and high bandwidth.
-
D.
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.
-
E.
SCSI over RDMA
SCSI over RDMA is a storage networking protocol that enables SCSI commands to be transported efficiently over Remote Direct Memory Access–capable networks for high-performance, low-latency data access.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: RDMA over InfiniBand Target entity description: RDMA over InfiniBand is a high-performance networking technology that enables direct memory access between computers over InfiniBand fabrics, minimizing CPU involvement and latency for data-intensive applications.
-
A.
RDMA over Converged Ethernet
RDMA over Converged Ethernet is a network protocol that enables Remote Direct Memory Access over Ethernet networks to provide low-latency, high-throughput data transfer commonly used in high-performance computing and data centers.
-
B.
RDMA over TCP/IP
RDMA over TCP/IP is a networking technology that provides remote direct memory access capabilities over standard TCP/IP networks, enabling low-latency, high-throughput data transfer without involving the host CPU.
-
C.
IP over InfiniBand
IP over InfiniBand is a networking technology that enables standard Internet Protocol (IP) traffic to run over high-speed InfiniBand fabrics, allowing IP-based applications to leverage InfiniBand’s low latency and high bandwidth.
-
D.
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.
-
E.
SCSI over RDMA
SCSI over RDMA is a storage networking protocol that enables SCSI commands to be transported efficiently over Remote Direct Memory Access–capable networks for high-performance, low-latency data access.
- F. None of above. chosen
Provenance (2 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798db79c819085e3a2526538726f |
completed | April 20, 2026, 7:07 p.m. |
Created at: April 16, 2026, 11:29 a.m.