Triple
T37149133
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RDMA over Converged Ethernet |
E920316
|
entity |
| Predicate | RoCEv1Encapsulation |
P143229
|
FINISHED |
| Object | Ethernet link layer |
—
|
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: Ethernet link layer | Statement: [RDMA over Converged Ethernet, RoCEv1Encapsulation, Ethernet link layer]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: RoCEv1Encapsulation Context triple: [RDMA over Converged Ethernet, RoCEv1Encapsulation, Ethernet link layer]
-
A.
encapsulationDirection
chosen
Indicates the direction in which one entity encloses, contains, or wraps around another within an encapsulation relationship.
-
B.
supportsVLANTagging
Indicates that one entity provides the capability for another entity or interface to handle and process VLAN-tagged network traffic.
-
C.
VLANIdentifierSizeBits
Indicates the number of bits used to represent a VLAN identifier in a networking context.
-
D.
congestionControlAlgorithm
Indicates that one entity uses, implements, or is associated with a particular congestion control algorithm in managing network traffic.
-
E.
switchingFabric
Indicates a relationship where data traffic is routed or switched between multiple endpoints through an intermediate switching infrastructure.
- F. None of above.
Provenance (3 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:15 p.m.