Triple
T22791797
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wedel Jarlsberg family |
E564130
|
entity |
| Predicate | notableEstate |
P18330
|
FINISHED |
| Object | Jarlsberg Manor |
—
|
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: Jarlsberg Manor | Statement: [Wedel Jarlsberg family, notableEstate, Jarlsberg Manor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jarlsberg Manor Context triple: [Wedel Jarlsberg family, notableEstate, Jarlsberg Manor]
-
A.
Jarlsberg Manor
chosen
Jarlsberg Manor is a historic Norwegian estate and manor house long associated with the noble Wedel Jarlsberg family.
-
B.
Jarlsberg hovedgård
Jarlsberg hovedgård is a historic Norwegian manor and former noble estate closely associated with the influential Wedel Jarlsberg family.
-
C.
Bjorkborn Manor
Bjorkborn Manor is a historic estate in Karlskoga, Sweden, best known as the last residence of dynamite inventor and Nobel Prize founder Alfred Nobel.
-
D.
Marienhof
Marienhof is a German television soap opera that gained popularity in the 1990s and 2000s for its portrayal of everyday life and relationships in a fictional Cologne neighborhood.
-
E.
Humlegården
Humlegården is a large historic park in central Stockholm known for its green spaces, walking paths, and recreational areas.
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd5778c81909a18317ff98e341c |
completed | April 29, 2026, 3:36 a.m. |
Created at: April 17, 2026, 3:30 p.m.