Triple
T36926780
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PPP Banyan VINES Control Protocol |
E913365
|
entity |
| Predicate | transportEncapsulation |
P200764
|
FINISHED |
| Object | PPP frames |
—
|
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: PPP frames | Statement: [PPP Banyan VINES Control Protocol, transportEncapsulation, PPP frames]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transportEncapsulation Context triple: [PPP Banyan VINES Control Protocol, transportEncapsulation, PPP frames]
-
A.
transportInterface
Indicates a relationship where one entity serves as the medium or mechanism through which another entity is transported or conveyed.
-
B.
transportProtocol
Indicates the communication protocol used to transport data between entities in a networked interaction.
-
C.
transportProcess
Indicates a process in which something is moved or carried from one place, state, or medium to another.
-
D.
encapsulationDirection
Indicates the direction in which one entity encloses, contains, or wraps around another within an encapsulation relationship.
-
E.
encapsulatesProtocol
Indicates that one entity implements and contains the functionality of a specific communication or interaction protocol on behalf of another entity.
- F. None of above. chosen
Provenance (4 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_69f76e896c988190880c130e01303dd4 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69ffab5adf2c819084700c5ea34615bf |
completed | May 9, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69ffaabffa208190b5214ca17cc8a5ea |
completed | May 9, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69ffab59fe408190b72f13016de9953c |
completed | May 9, 2026, 9:47 p.m. |
Created at: May 3, 2026, 4:13 p.m.