Triple
T23070829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johan Caspar Herman Wedel-Jarlsberg |
E575188
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Wedel-Jarlsberg |
—
|
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: Wedel-Jarlsberg | Statement: [Johan Caspar Herman Wedel-Jarlsberg, familyName, Wedel-Jarlsberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wedel-Jarlsberg Context triple: [Johan Caspar Herman Wedel-Jarlsberg, familyName, Wedel-Jarlsberg]
-
A.
Wedel-Jarlsberg
chosen
Wedel-Jarlsberg is a notable Norwegian noble family historically influential in politics, landownership, and public life in Norway.
-
B.
Widdersberg
Widdersberg is a small village that forms one of the local subdivisions of the municipality of Münsing in Bavaria, Germany.
-
C.
Wedel
Wedel is a town on the outskirts of Hamburg, Germany, known for being a suburban terminus of the city's S-Bahn network.
-
D.
Lonstein
Lonstein is a surname of likely Ashkenazi Jewish origin borne by various individuals and families.
-
E.
Weilerswist
Weilerswist is a municipality in the Rhein-Erft district of North Rhine-Westphalia, Germany, known for its rural character and proximity to the cities of Cologne and Bonn.
- 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_69e245bd6e4c8190bb8942245b68cad5 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f18c5f17348190ab92cfdae9bcaeba |
completed | April 29, 2026, 4:43 a.m. |
Created at: April 17, 2026, 3:56 p.m.