Triple
T23386716
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gemen Castle |
E593903
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Borken |
—
|
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: Borken | Statement: [Gemen Castle, locatedIn, Borken]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Borken Context triple: [Gemen Castle, locatedIn, Borken]
-
A.
Borken
chosen
Borken is a town in western Germany that serves as an administrative and commercial center in the state of North Rhine-Westphalia.
-
B.
Borghorst
Borghorst is a district of the German town Steinfurt in North Rhine-Westphalia, known historically for its textile industry and regional cultural heritage.
-
C.
Hagen
Hagen is a city in the Ruhr region of North Rhine-Westphalia in western Germany, known historically as an industrial and transport hub.
-
D.
Hagen
Hagen is a surname of German origin borne by various notable individuals across fields such as music, sports, and academia.
-
E.
Hagen
Hagen is a formidable and cunning warrior in the medieval German epic "Nibelungenlied," best known for betraying and killing the hero Siegfried.
- 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_69e25d2754fc819085deea939bde60ab |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a498fd08819085e90a872d9d0c7a |
completed | April 29, 2026, 6:26 a.m. |
Created at: April 17, 2026, 5:35 p.m.