Triple
T730939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carel Fabritius |
E14827
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Aeltge Velthuys
Aeltge Velthuys was the wife of Dutch Golden Age painter Carel Fabritius, known primarily through her connection to the artist.
|
E126837
|
NE FINISHED |
How this triple was built (4 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: Aeltge Velthuys | Statement: [Carel Fabritius, spouse, Aeltge Velthuys]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aeltge Velthuys Context triple: [Carel Fabritius, spouse, Aeltge Velthuys]
-
A.
Jan D'Alquen
Jan D'Alquen is a cinematographer best known for his work on the classic coming-of-age film "American Graffiti."
-
B.
Willem
Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
-
C.
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.
-
D.
Michiel
Michiel is a Dutch given name most famously borne by the 17th-century admiral Michiel de Ruyter.
-
E.
Robrecht
Robrecht is a Dutch and Flemish given name, cognate with Robert, traditionally borne by men in the Low Countries.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Aeltge Velthuys Triple: [Carel Fabritius, spouse, Aeltge Velthuys]
Generated description
Aeltge Velthuys was the wife of Dutch Golden Age painter Carel Fabritius, known primarily through her connection to the artist.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Aeltge Velthuys Target entity description: Aeltge Velthuys was the wife of Dutch Golden Age painter Carel Fabritius, known primarily through her connection to the artist.
-
A.
Jan D'Alquen
Jan D'Alquen is a cinematographer best known for his work on the classic coming-of-age film "American Graffiti."
-
B.
Willem
Willem is a given name, primarily used in Dutch-speaking regions, that corresponds to the English name William.
-
C.
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.
-
D.
Michiel
Michiel is a Dutch given name most famously borne by the 17th-century admiral Michiel de Ruyter.
-
E.
Robrecht
Robrecht is a Dutch and Flemish given name, cognate with Robert, traditionally borne by men in the Low Countries.
- F. None of above. chosen
Provenance (5 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_69ac4bf512bc81908ff403ce87337a0d |
completed | March 7, 2026, 4:01 p.m. |
| NEDg | Description generation | batch_69ac4f7da1b48190b758c1900ef5bc8f |
completed | March 7, 2026, 4:17 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac4fd709e88190b7082b7111e24832 |
completed | March 7, 2026, 4:18 p.m. |
Created at: March 1, 2026, 7:37 p.m.