Triple
T8226414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Classis Germanica |
E192182
|
entity |
| Predicate | typeOfFrontierUnit |
P81735
|
FINISHED |
| Object | limes defense force |
—
|
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: limes defense force | Statement: [Classis Germanica, typeOfFrontierUnit, limes defense force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFrontierUnit Context triple: [Classis Germanica, typeOfFrontierUnit, limes defense force]
-
A.
borderingUnitType
Indicates that one unit is adjacent to another unit of a specified type along a shared boundary.
-
B.
oversawUnitType
Indicates that an entity had supervisory or managerial responsibility over a particular type or category of unit.
-
C.
typeOfUnit
Indicates that one entity specifies the kind or category of measurement unit that the other entity belongs to.
-
D.
featuredUnitType
Indicates that a particular unit type is highlighted or given special prominence relative to other unit types.
-
E.
coreUnitType
Indicates that one entity is classified as the primary or fundamental type/category to which another entity (a core unit) belongs.
- 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_69ca82db5b90819085d1ad7c2e27bfcc |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb77fc10f48190b7e241c89885a478 |
completed | March 31, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69cb36af41e081909dee92b9bc4947f1 |
completed | March 31, 2026, 2:51 a.m. |
| PDg | Predicate description generation | batch_69cb4d9b03108190a6785834f21ff75e |
completed | March 31, 2026, 4:29 a.m. |
Created at: March 30, 2026, 5:45 p.m.