Triple
T37164402
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DVB-GSE |
E920755
|
entity |
| Predicate | supportsEncapsulationOf |
P33248
|
FINISHED |
| Object | IP packets |
—
|
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: IP packets | Statement: [DVB-GSE, supportsEncapsulationOf, IP packets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsEncapsulationOf Context triple: [DVB-GSE, supportsEncapsulationOf, IP packets]
-
A.
encapsulation
chosen
Indicates that one entity encloses, contains, or wraps another entity or set of details within a defined boundary, often hiding internal structure from external access.
-
B.
supportsInclusion
Indicates that one entity actively promotes, enables, or upholds the inclusion and equitable participation of another entity or group.
-
C.
supportsValidationOf
Indicates that one entity provides the mechanisms or conditions necessary for another entity to be checked or verified for correctness or compliance.
-
D.
encapsulationMode
Indicates how one entity is wrapped, contained, or isolated within another or within a defined boundary.
-
E.
supportsImplementationOf
Indicates that one entity provides the necessary resources, framework, or assistance for another entity to be carried out, realized, or put into practice.
- 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_69f76ea0429081908c711b55599eac3c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:15 p.m.