Triple
T8226635
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Classis Pannonica |
E192188
|
entity |
| Predicate | supportedUnitType |
P55850
|
FINISHED |
| Object | Roman legions |
—
|
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: Roman legions | Statement: [Classis Pannonica, supportedUnitType, Roman legions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportedUnitType Context triple: [Classis Pannonica, supportedUnitType, Roman legions]
-
A.
supportedUnit
Indicates that one entity provides assistance, resources, or backing to another entity functioning as a unit or sub-organization.
-
B.
typicalSupportedUnitType
chosen
Indicates the kind or category of unit that an entity is normally designed or expected to support.
-
C.
supportUnits
Indicates that one entity provides assistance, resources, or reinforcement to another entity, often in an operational or functional context.
-
D.
basedUnitType
Indicates that one unit is defined or derived in terms of another underlying (base) unit type.
-
E.
associatedUnitType
Indicates that one entity is linked to or characterized by a particular type or category of unit.
- 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_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. |
Created at: March 30, 2026, 5:46 p.m.