Triple
T18624384
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaak Gabriëls |
E455240
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Jaak Gabriëls |
—
|
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: Jaak Gabriëls | Statement: [Jaak Gabriëls, name, Jaak Gabriëls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jaak Gabriëls Context triple: [Jaak Gabriëls, name, Jaak Gabriëls]
-
A.
Jaak Gabriëls
chosen
Jaak Gabriëls is a Belgian liberal politician known for his roles in national and regional government, including serving as a federal minister and mayor.
-
B.
Johan de Jonge
Johan de Jonge is a person notable enough to be recognized as a distinguished bearer of the surname "de Jonge."
-
C.
Jules Cronjager
Jules Cronjager was an early 20th-century cinematographer and industry figure who helped shape the professional community of American cameramen.
-
D.
Sidney van den Bergh
Sidney van den Bergh is a Canadian astronomer renowned for his work on galaxies and galaxy clusters, including the discovery of several dwarf galaxies.
-
E.
August Brenninkmeijer
August Brenninkmeijer was a 19th-century Dutch-German entrepreneur best known as a co-founder of the international clothing retail company C&A.
- 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_69d8d38cc7948190a55ea64e5638994e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e54f039b408190b51fe770a4c530ec |
completed | April 19, 2026, 9:54 p.m. |
Created at: April 10, 2026, 11:46 a.m.