Triple
T25945726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman province of Dacia |
E653833
|
entity |
| Predicate | previousCapitalOfDacianKingdom |
P177091
|
FINISHED |
| Object | Sarmizegetusa Regia |
—
|
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: Sarmizegetusa Regia | Statement: [Roman province of Dacia, previousCapitalOfDacianKingdom, Sarmizegetusa Regia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousCapitalOfDacianKingdom Context triple: [Roman province of Dacia, previousCapitalOfDacianKingdom, Sarmizegetusa Regia]
-
A.
lastDacianKing
Indicates that the subject is the final ruler to hold the title of king within the Dacian realm or polity.
-
B.
associatedDynastyCapital
Indicates a relationship where a dynasty is linked to the city that served as its capital.
-
C.
ancientCapitalLocatedIn
Indicates that a city served as the capital of an ancient polity or civilization and was geographically situated within a specified region or territory.
-
D.
capitalOfOneCaesar
Indicates that one entity serves as the capital city associated with a specific Caesar (ruler) in a given context.
-
E.
romanProvinceCapital
Indicates that one place served as the administrative capital of a specified Roman province.
- 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_69e7ab40ac788190a771bc499eb1ae5f |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6f85bfba48190aba95b40642a8ca7 |
completed | May 3, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f6f65fd1d08190b88e5e68ba268500 |
completed | May 3, 2026, 7:16 a.m. |
| PDg | Predicate description generation | batch_69f6f854486c81909396d944a55e03ab |
completed | May 3, 2026, 7:25 a.m. |
Created at: April 22, 2026, 8:43 a.m.