Triple
T11351423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iWARP |
E268846
|
entity |
| Predicate | offloads |
P68985
|
FINISHED |
| Object | RDMA operations to NIC hardware |
—
|
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: RDMA operations to NIC hardware | Statement: [iWARP, offloads, RDMA operations to NIC hardware]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offloads Context triple: [iWARP, offloads, RDMA operations to NIC hardware]
-
A.
offloadingMethod
chosen
Indicates the method or process by which something is transferred or offloaded from one entity, system, or location to another.
-
B.
offsets
Indicates that one entity counterbalances, compensates for, or reduces the effect, value, or impact of another.
-
C.
off
Indicates that one entity is separated from, away from, or no longer attached to another entity or reference point.
-
D.
outs
Indicates that one entity defeats, surpasses, or performs better than another in a competitive or comparative context.
-
E.
spinOffWork
Indicates that one work is derived from, based on, or created as a spin-off of another preexisting work.
- 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_69d6aacbe18081909e5fadb50082dd96 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d80148e2048190a716b515d78efdd1 |
completed | April 9, 2026, 7:43 p.m. |
| PD | Predicate disambiguation | batch_69d7e6f8aeb4819080476f16a69b2ee3 |
completed | April 9, 2026, 5:50 p.m. |
Created at: April 8, 2026, 9:33 p.m.