Triple
T16109523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Henri Bontenbal |
E390836
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Henri Bontenbal |
E390836
|
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: Henri Bontenbal | Statement: [Henri Bontenbal, name, Henri Bontenbal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henri Bontenbal Context triple: [Henri Bontenbal, name, Henri Bontenbal]
-
A.
Henri Bontenbal
chosen
Henri Bontenbal is a Dutch politician who serves as the leader of the Christian Democratic Appeal (CDA) and is known for his focus on energy and climate policy.
-
B.
Jan van Bijlert
Jan van Bijlert was a Dutch Golden Age painter associated with the Utrecht Caravaggisti, known for his religious, genre, and portrait works influenced by Caravaggio’s dramatic use of light and shadow.
-
C.
Gerard Joling
Gerard Joling is a Dutch singer and television personality known for his high-pitched vocals, pop hits since the 1980s, and prominent role in Dutch entertainment.
-
D.
Wim de Wit
Wim de Wit is a Dutch art historian and curator known for his work on modern architecture and design.
-
E.
Frans Andriessen
Frans Andriessen was a Dutch politician who served prominently in the European Commission, becoming one of its most senior leaders and shaping key economic and trade policies in the late 20th century.
- 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_69d87f1a8dd881909f1de6ef78849874 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2016665c0819081aa7a44b1d08183 |
completed | April 17, 2026, 9:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f39008c819095ad8512eb119ee8 |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5 a.m.