Triple
T18992137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Marche |
E464711
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Aubusson |
—
|
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: Aubusson | Statement: [La Marche, contains, Aubusson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aubusson Context triple: [La Marche, contains, Aubusson]
-
A.
Aubusson
chosen
Aubusson is a town in central France renowned for its centuries-old tradition of tapestry and carpet weaving.
-
B.
Limoges
Limoges is a historic city in central France renowned for its fine porcelain production and medieval architecture.
-
C.
Sèvres
Sèvres is a commune in the southwestern suburbs of Paris, France, historically notable as the site where the post–World War I Treaty of Sèvres was concluded.
-
D.
Langres
Langres is a historic fortified town in northeastern France known for its well-preserved ramparts and as the birthplace of Enlightenment philosopher Denis Diderot.
-
E.
Bezannes
Bezannes is a commune in northeastern France near Reims, known for hosting the Champagne-Ardenne TGV high-speed railway station.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d67eedc88190bfb7b327b47db76d |
completed | April 20, 2026, 7:32 a.m. |
Created at: April 10, 2026, 12:01 p.m.