Triple
T22785228
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Palatine of Hungary |
E563944
|
entity |
| Predicate | residence |
P75
|
FINISHED |
| Object | Pressburg |
—
|
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: Pressburg | Statement: [Palatine of Hungary, residence, Pressburg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pressburg Context triple: [Palatine of Hungary, residence, Pressburg]
-
A.
Pozsony
chosen
Pozsony is the historical Hungarian name for the city now known as Bratislava, the capital of Slovakia.
-
B.
Lieboch
Lieboch is a small municipality in the Austrian state of Styria, located just southwest of the city of Graz.
-
C.
Freistadt
Freistadt is a historic small city in Upper Austria known for its well-preserved medieval town center and role as a local cultural and economic hub.
-
D.
Kapfenberg
Kapfenberg is an industrial town in southeastern Austria known for its steel production and location in the state of Styria.
-
E.
Visegrád
Visegrád is a historic town in northern Hungary on the Danube River, renowned for its medieval castle and royal palace that once served as a seat of Hungarian kings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c30b4dc8190a5e23f4ce7feb300 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.