Triple
T730911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carel Fabritius |
E14827
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Carel |
E6688
|
NE FINISHED |
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: Carel | Statement: [Carel Fabritius, givenName, Carel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carel Context triple: [Carel Fabritius, givenName, Carel]
-
A.
Jan Verkade
Jan Verkade was a Dutch Post-Impressionist painter associated with the Pont-Aven School and the Nabis, known for his synthetist style and later life as a Benedictine monk.
-
B.
Pieter
Pieter is the given first name of the influential Afrikaans poet, playwright, and essayist N. P. van Wyk Louw.
-
C.
Willem Delff
Willem Delff was a Dutch Golden Age engraver and painter from Delft, known for his detailed reproductive engravings after prominent artists of his time.
-
D.
Willem
chosen
Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
-
E.
Karel
Karel is a given name, commonly used in Central and Eastern Europe, that corresponds to the English name Charles.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69a4934d9930819099eed80096b0597d |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5c40b6481909db9efd7310850b3 |
completed | March 1, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a79280fa5c819098397cc1b5c626c0 |
completed | March 4, 2026, 2:01 a.m. |
Created at: March 1, 2026, 7:37 p.m.