Triple
T19303213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Porrentruy Castle |
E482753
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Porrentruy |
—
|
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: Porrentruy | Statement: [Porrentruy Castle, locatedIn, Porrentruy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Porrentruy Context triple: [Porrentruy Castle, locatedIn, Porrentruy]
-
A.
Porrentruy
chosen
Porrentruy is a historic town in northwestern Switzerland known for its medieval castle and role as a regional center in the canton of Jura.
-
B.
Verviers
Verviers is a city in eastern Belgium known historically for its textile industry and as a regional center in the province of Liège.
-
C.
Esch-sur-Sûre
Esch-sur-Sûre is a small historic town in northwestern Luxembourg, known for its medieval castle ruins and picturesque setting along a bend of the Sûre River.
-
D.
Céligny
Céligny is a small, affluent Swiss village on the shores of Lake Geneva, known for its picturesque setting and as the burial place of actor Richard Burton.
-
E.
Buizingen
Buizingen is a village and suburb of Halle in Flemish Brabant, Belgium, known in part for the 2010 train collision that occurred near its railway station.
- 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_69d8e8d04d5c8190baa816986f2b1d1e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e604c5903c819090b3f89c3f33b005 |
completed | April 20, 2026, 10:49 a.m. |
Created at: April 10, 2026, 1:31 p.m.