Triple
T9949148
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sombreffe |
E195283
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Gembloux |
E747984
|
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: Gembloux | Statement: [Sombreffe, locatedNear, Gembloux]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gembloux Context triple: [Sombreffe, locatedNear, Gembloux]
-
A.
Gembloux
chosen
Gembloux is a town in the Walloon region of Belgium known for its historic center and agricultural university.
-
B.
Kevelaer
Kevelaer is a renowned German pilgrimage town in North Rhine-Westphalia, famous as one of Europe’s most important Marian shrines and a major destination for Catholic pilgrims.
-
C.
Berlencourt
Berlencourt is a small commune in northern France, located within the Nord department in the Hauts-de-France region.
-
D.
Margraten
Margraten is a village in the Dutch province of Limburg best known for hosting the Netherlands American Cemetery, a major World War II military burial ground for U.S. soldiers.
-
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_69ca82e96a108190932bd1fc4acd73a0 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cdb65a4e6c8190968192a24aad1b7d |
completed | April 2, 2026, 12:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d23d5c6fdc81909b44d0b321201222 |
completed | April 5, 2026, 10:45 a.m. |
Created at: March 30, 2026, 8:45 p.m.