Triple
T17421756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koning |
E423632
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | De Koninck |
—
|
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: De Koninck | Statement: [Koning, hasVariant, De Koninck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: De Koninck Context triple: [Koning, hasVariant, De Koninck]
-
A.
Koninck
chosen
Koninck is a variant form of the Dutch surname "Koning," which is derived from the word for "king."
-
B.
Jan Kempdorp
Jan Kempdorp is a small agricultural and service town in South Africa’s Northern Cape province.
-
C.
Laurens van den Acker
Laurens van den Acker is a Dutch automobile designer best known for leading Renault’s design strategy and creating several of its modern, highly successful models.
-
D.
Willem Arondeus
Willem Arondeus was a Dutch artist and openly gay resistance fighter during World War II, best known for his role in the 1943 attack on Amsterdam’s population registry to hinder Nazi persecution of Jews.
-
E.
Johan de Jonge
Johan de Jonge is a person notable enough to be recognized as a distinguished bearer of the surname "de Jonge."
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e44237f2cc819083ca0e7e00d828fb |
completed | April 19, 2026, 2:47 a.m. |
Created at: April 10, 2026, 5:46 a.m.