Triple
T20400001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intel Omni-Path Architecture |
E500305
|
entity |
| Predicate | networkTopologySupport |
P33685
|
FINISHED |
| Object | fat-tree topologies |
—
|
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: fat-tree topologies | Statement: [Intel Omni-Path Architecture, networkTopologySupport, fat-tree topologies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkTopologySupport Context triple: [Intel Omni-Path Architecture, networkTopologySupport, fat-tree topologies]
-
A.
usesTopology
chosen
Indicates that one entity employs, is based on, or operates according to a particular topology defined or provided by another entity.
-
B.
networkModel
Indicates a relationship where an entity is represented or organized according to a specific network-based structure or framework.
-
C.
networkMode
Indicates the type or configuration of connectivity or communication method used within a network or between networked entities.
-
D.
hasTopology
Indicates that one entity possesses, exhibits, or is characterized by a particular structural or spatial configuration defined by the other entity.
-
E.
networkMap
Indicates a mapping relationship that shows how elements in a network are connected or arranged relative to one another.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798db79c819085e3a2526538726f |
completed | April 20, 2026, 7:07 p.m. |
| PD | Predicate disambiguation | batch_69e5765d7cb48190adec18d6d1e3d263 |
completed | April 20, 2026, 12:42 a.m. |
Created at: April 16, 2026, 11:29 a.m.