Triple
T8592448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Varangians |
E203461
|
entity |
| Predicate | usedRoutes |
P83751
|
FINISHED |
| Object | river routes of Eastern Europe |
—
|
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: river routes of Eastern Europe | Statement: [Varangians, usedRoutes, river routes of Eastern Europe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedRoutes Context triple: [Varangians, usedRoutes, river routes of Eastern Europe]
-
A.
routesFrom
Indicates that something (such as a path, connection, or communication) originates at one entity and is directed or carried from that source entity toward another.
-
B.
numberOfRoutes
Indicates the total count of distinct routes or paths associated with a given entity or between specified entities.
-
C.
usesRoutingType
Indicates that one entity employs or operates according to a specific routing type or routing method associated with another entity.
-
D.
firstRoutes
Indicates that one route or path is the initial or primary route taken or assigned among a set of possible routes.
-
E.
parallelRoute
Indicates that one route runs alongside and in the same general direction as another route without intersecting it.
- 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_69ca832a7f108190b4e4f5648abf4aa2 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cc46c5e8888190b721e791c449b0df |
completed | March 31, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69cc454504448190aaad2af8b17357cd |
completed | March 31, 2026, 10:05 p.m. |
| PDg | Predicate description generation | batch_69cc46c330bc8190a9b644078881c6ff |
completed | March 31, 2026, 10:12 p.m. |
Created at: March 30, 2026, 6:23 p.m.