Triple
T33475024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Valeria (Roman province) |
E857295
|
entity |
| Predicate | frontierAlong |
P165704
|
FINISHED |
| Object | Danube limes |
—
|
NE NERFINISHED |
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: Danube limes | Statement: [Valeria (Roman province), frontierAlong, Danube limes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontierAlong Context triple: [Valeria (Roman province), frontierAlong, Danube limes]
-
A.
frontierWith
chosen
Indicates that two regions or territories share a common boundary or border, especially one marking the edge of settled or controlled area.
-
B.
frontierSystem
Indicates a system that lies at or near the boundary or edge of a defined region, domain, or area of control.
-
C.
frontLineBetween
Indicates that a boundary or line of direct confrontation exists separating two opposing sides or regions.
-
D.
boundaryCurrentAlong
Indicates that the current boundary of one entity runs along or coincides with the boundary of another entity.
-
E.
northernFrontier
Indicates that one entity serves as the northern boundary, edge, or frontier region relative to another entity.
- 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_69f3497472508190b300ebd3fd402367 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f6e501c1fc819081b14287930e834d |
completed | May 3, 2026, 6:02 a.m. |
| PD | Predicate disambiguation | batch_69f6e3da41948190a4cfe866ce184f73 |
completed | May 3, 2026, 5:57 a.m. |
Created at: May 1, 2026, 1:38 a.m.