Triple
T12443087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wattrelos |
E297324
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Mouscron |
E1027756
|
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: Mouscron | Statement: [Wattrelos, twinTown, Mouscron]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mouscron Context triple: [Wattrelos, twinTown, Mouscron]
-
A.
Mouscron
chosen
Mouscron is a Belgian city in the province of Hainaut, near the French border in the region of Wallonia.
-
B.
Gosselies
Gosselies is a district of the city of Charleroi in Wallonia, Belgium, known for its proximity to Brussels South Charleroi Airport and its industrial and aeronautical activities.
-
C.
Izegem
Izegem is a town in the Belgian province of West Flanders, known historically for its shoe and brush industries.
-
D.
Mechelen
Mechelen is a historic city in the Flemish region of Belgium, known for its rich architectural heritage, medieval center, and prominent role in the Low Countries’ political and religious history.
-
E.
St. Truiden
St. Truiden is a historic Belgian city in the Limburg region, known for its medieval architecture and fruit-growing countryside.
- 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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d8fd9848190a83410353d88ea8d |
completed | April 10, 2026, 7:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a16408081909097d7e3ab750a27 |
completed | May 3, 2026, 8:40 a.m. |
Created at: April 8, 2026, 9:55 p.m.