Triple
T22704373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frans Kellendonk |
E561408
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Frans Kellendonk |
—
|
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: Frans Kellendonk | Statement: [Frans Kellendonk, name, Frans Kellendonk]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frans Kellendonk Context triple: [Frans Kellendonk, name, Frans Kellendonk]
-
A.
Frans Kellendonk
chosen
Frans Kellendonk was a Dutch novelist and essayist known for his intellectually rich, stylistically precise fiction that explored themes of identity, religion, and society.
-
B.
Frans Wouters
Frans Wouters was a 17th-century Flemish Baroque painter known for his small-scale cabinet paintings and collaborations with prominent artists in Antwerp.
-
C.
Roeland Fernhout
Roeland Fernhout is a Dutch actor known for his work in film, television, and theater, particularly within contemporary Dutch cinema.
-
D.
Geert Bourgeois
Geert Bourgeois is a Belgian Flemish nationalist politician and former Minister-President of Flanders, known as a founding figure and key leader of the New Flemish Alliance (N-VA).
-
E.
Henk Van Eeghen
Henk Van Eeghen is a film editor known for his work on the movie "Miracle Mile."
- 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_69e2454e615481909c177440be559d2c |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f178cca1e48190bbe7910f13692803 |
completed | April 29, 2026, 3:19 a.m. |
Created at: April 17, 2026, 3:16 p.m.