Triple
T27572733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CLNS |
E696075
|
entity |
| Predicate | fragmentationSupport |
P203
|
FINISHED |
| Object | supports packet fragmentation and reassembly |
—
|
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: supports packet fragmentation and reassembly | Statement: [CLNS, fragmentationSupport, supports packet fragmentation and reassembly]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fragmentationSupport Context triple: [CLNS, fragmentationSupport, supports packet fragmentation and reassembly]
-
A.
canBeFragmented
Indicates that something is capable of being broken, divided, or split into smaller parts or fragments.
-
B.
fragmentationLevel
Indicates the degree to which something is broken into smaller, separate parts or segments.
-
C.
supportsOnlineDefragmentation
Indicates that the subject provides the capability to perform defragmentation operations while remaining online and operational.
-
D.
hasFragments
Indicates that an entity is composed of, contains, or is associated with one or more smaller constituent parts or pieces.
-
E.
supportsFeature
chosen
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of 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_69ef53891af88190a193c5e2a1dac9b1 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62fed98888190bdc01137b65acbb6 |
completed | May 2, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:44 p.m.