Triple
T21896218
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mayken Verhulst |
E540685
|
entity |
| Predicate | alsoKnownAs |
P39
|
FINISHED |
| Object | Mayken Bessemers |
—
|
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: Mayken Bessemers | Statement: [Mayken Verhulst, alsoKnownAs, Mayken Bessemers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mayken Bessemers Context triple: [Mayken Verhulst, alsoKnownAs, Mayken Bessemers]
-
A.
Maria Bessemers
chosen
Maria Bessemers, better known as Mayken Verhulst, was a prominent 16th-century Flemish painter and influential printmaker who played a key role in the artistic training of her grandsons, the Brueghel painters.
-
B.
Tessa Berens
Tessa Berens is a fictional character from the work titled "The Silence."
-
C.
Melanie Nissen
Melanie Nissen is a music industry figure best known as the co-founder of the influential Los Angeles punk label Slash Records.
-
D.
Jessica De Gouw
Jessica De Gouw is an Australian actress known for her work in film and television, including roles in series like "Arrow" and "Dracula."
-
E.
Annemarie Dyckhoff
Annemarie Dyckhoff is best known as the wife of Scottish science fiction author Iain M. Banks.
- 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_69e0c47a95908190ae3e19b716accb3d |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f11fc700c08190a470fe1ad76c8509 |
completed | April 28, 2026, 8:59 p.m. |
Created at: April 16, 2026, 7:07 p.m.