Triple
T14315112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ethernet switch |
E354934
|
entity |
| Predicate | segregates |
P1175
|
FINISHED |
| Object | collision domains |
—
|
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: collision domains | Statement: [Ethernet switch, segregates, collision domains]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: segregates Context triple: [Ethernet switch, segregates, collision domains]
-
A.
separates
chosen
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
B.
segregatedFor
Indicates that one entity is separated or set apart from others specifically for the use, benefit, or association of another entity.
-
C.
segregationBasis
Indicates the criterion or characteristic used as the basis for separating or distinguishing one group or set from another.
-
D.
separatedIn
Indicates that two or more entities, once together or associated, have been divided, split, or otherwise placed into distinct parts, groups, or locations.
-
E.
separatesState
Indicates that one entity serves as a dividing boundary or barrier between two distinct states or regions.
- 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_69d8278ed42c8190b9f882dcce611347 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de85b49e5481909b9ffab2d922e284 |
completed | April 14, 2026, 6:21 p.m. |
| PD | Predicate disambiguation | batch_69de2a9515f4819081aabf251bca5878 |
completed | April 14, 2026, 11:52 a.m. |
Created at: April 10, 2026, 1:12 a.m.