Triple
T25945754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman province of Dacia |
E653833
|
entity |
| Predicate | territoryAfterAbandonment |
P59198
|
FINISHED |
| Object | Dacia Aureliana |
—
|
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: Dacia Aureliana | Statement: [Roman province of Dacia, territoryAfterAbandonment, Dacia Aureliana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territoryAfterAbandonment Context triple: [Roman province of Dacia, territoryAfterAbandonment, Dacia Aureliana]
-
A.
laterTerritory
chosen
Indicates that one territory is a subsequent or successor territory to another in time.
-
B.
lostTerritoryBy
Indicates that one entity has had control or ownership of a territory taken away by another entity.
-
C.
countryCedingTerritory
Indicates that one country is formally transferring control or ownership of a portion of its territory to another entity.
-
D.
landsPreviouslyBelongedTo
Indicates that the specified lands were owned, controlled, or possessed by a different party at an earlier time.
-
E.
returnedTerritoryName
Indicates the name of a territory that has been given back or restored to a previous owner or controlling 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f627aedf548190bc9f53c8a2d67b50 |
completed | May 2, 2026, 4:34 p.m. |
| PD | Predicate disambiguation | batch_69f623a4e1048190bbb8dd1253fdcee9 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 22, 2026, 8:43 a.m.