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.