Triple
T25945730
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman province of Dacia |
E653833
|
entity |
| Predicate | wasFrontierProvinceOf |
P25984
|
FINISHED |
| Object | Roman Empire |
—
|
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: Roman Empire | Statement: [Roman province of Dacia, wasFrontierProvinceOf, Roman Empire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasFrontierProvinceOf Context triple: [Roman province of Dacia, wasFrontierProvinceOf, Roman Empire]
-
A.
wasFrontierRegion
Indicates that a region historically functioned as a frontier area, marking a boundary or border zone between larger political or cultural entities.
-
B.
wasFrontierBetween
Indicates that one entity historically served as the boundary or border region separating two other entities.
-
C.
laterProvince
Indicates that one administrative region or province succeeds another in time, coming into existence or effect after the other.
-
D.
wasCoreTerritoryOf
Indicates that a region historically formed the central or most important territorial area belonging to a particular political or cultural entity.
-
E.
formerProvince
chosen
Indicates that an entity was previously a province of another entity but no longer holds that administrative status.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f60464d4988190bc39b78c8e418547 |
completed | May 2, 2026, 2:04 p.m. |
| PD | Predicate disambiguation | batch_69f4a10480748190a2e67bd399fc435d |
completed | May 1, 2026, 12:48 p.m. |
Created at: April 22, 2026, 8:43 a.m.