Triple
T17427591
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bois du Cazier mining disaster of 1956 |
E423778
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Marcinelle |
—
|
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: Marcinelle | Statement: [Bois du Cazier mining disaster of 1956, location, Marcinelle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcinelle Context triple: [Bois du Cazier mining disaster of 1956, location, Marcinelle]
-
A.
Marcinelle
chosen
Marcinelle is a district of Charleroi in Wallonia, Belgium, historically known as a coal-mining community and the site of the 1956 Bois du Cazier mining disaster.
-
B.
Tettenweis
Tettenweis is a small Bavarian village in Germany known as the birthplace of the Symbolist painter Franz von Stuck.
-
C.
Malmedy
Malmedy is a historic town and municipality in eastern Belgium, known for its Ardennes setting, traditional carnival, and proximity to the Battle of the Bulge sites.
-
D.
Martelange
Martelange is a small Belgian town known for straddling the border with Luxembourg and serving as a local commercial and transit hub.
-
E.
Wytschaete
Wytschaete is a village in West Flanders, Belgium, that was a strategically important position on the Western Front during World War I.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e448fdc1348190985db52c8c74c394 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.