Triple
T18749604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulrika Francke |
E458492
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Ulrika |
—
|
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: Ulrika | Statement: [Ulrika Francke, givenName, Ulrika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ulrika Context triple: [Ulrika Francke, givenName, Ulrika]
-
A.
Ulrika
chosen
Ulrika is a central character in the Swedish musical "Kristina från Duvemåla," known as a strong-willed and controversial woman whose life intertwines with the emigrant community.
-
B.
Ulrike
Ulrike is a German given name, typically feminine, derived from the name Ulrich and associated with German-speaking countries.
-
C.
Ulrika Wolf-Knuts
Ulrika Wolf-Knuts is a Finnish folklorist and academic who has served as chancellor of Åbo Akademi University.
-
D.
Gunilla
Gunilla is a Scandinavian female given name, particularly common in Sweden and other Nordic countries.
-
E.
Henrike
Henrike is a feminine given name of German origin, serving as the female form of Heinrich.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579eb7350819099d7291207781116 |
completed | April 20, 2026, 12:57 a.m. |
Created at: April 10, 2026, 11:51 a.m.