Triple
T7427803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EIGRP |
E171411
|
entity |
| Predicate | routingCategory |
P12563
|
FINISHED |
| Object | hybrid routing protocol |
—
|
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: hybrid routing protocol | Statement: [EIGRP, routingCategory, hybrid routing protocol]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routingCategory Context triple: [EIGRP, routingCategory, hybrid routing protocol]
-
A.
routeCategory
Indicates the classification or type assigned to a route within a transportation or path network.
-
B.
routingBasis
chosen
Indicates the principle or criterion used to determine how something is directed, routed, or assigned among possible paths or destinations.
-
C.
routerTypes
Indicates that one entity specifies or categorizes the types or kinds of routers associated with another entity.
-
D.
route
Indicates that one entity serves as a path or course used to travel or move between locations associated with another entity.
-
E.
routeFamily
Indicates a familial or hierarchical relationship between routes, such as one route being derived from, grouped with, or subordinate to another within a routing structure.
- 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_69c68a63491881909281f73d4d5643bf |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f306bfe481909f99f6792de95ffc |
completed | March 27, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69c6f03648d08190b862d07fef71210c |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:12 p.m.