Triple
T8923671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berchem-Sainte-Agathe |
E212486
|
entity |
| Predicate | hasFrenchName |
P744
|
FINISHED |
| Object | Berchem-Sainte-Agathe |
E534792
|
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: Berchem-Sainte-Agathe | Statement: [Berchem-Sainte-Agathe, hasFrenchName, Berchem-Sainte-Agathe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Berchem-Sainte-Agathe Context triple: [Berchem-Sainte-Agathe, hasFrenchName, Berchem-Sainte-Agathe]
-
A.
Berchem-Sainte-Agathe
chosen
Berchem-Sainte-Agathe is a small, predominantly residential municipality in the Brussels-Capital Region of Belgium.
-
B.
Berchem
Berchem is a district of the Belgian city of Antwerp, known for its residential neighborhoods, Art Nouveau architecture, and vibrant local culture.
-
C.
Mont-Saint-Martin
Mont-Saint-Martin is a commune in northeastern France notable for lying at the junction of the French, Belgian, and Luxembourgish borders.
-
D.
Strépy-Bracquegnies
Strépy-Bracquegnies is a village in the Walloon region of Belgium, known in part for its proximity to the Strépy-Thieu boat lift.
-
E.
Comines
Comines is a town situated along the Lys River in the historic Flanders region on the border between France and Belgium.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6652d63881908821c8735984322a |
completed | April 1, 2026, 12:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba5480d48190bf126caaa882d39e |
completed | April 3, 2026, 1:02 p.m. |
Created at: March 30, 2026, 6:56 p.m.