Triple
T1622754
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ES Troyes AC |
E35069
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Troyes |
E73536
|
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: Troyes | Statement: [ES Troyes AC, location, Troyes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Troyes Context triple: [ES Troyes AC, location, Troyes]
-
A.
Troyes
chosen
Troyes is a historic city in northeastern France, known for its well-preserved medieval old town, half-timbered houses, and Gothic churches.
-
B.
Reims
Reims is a historic city in northeastern France known for its Gothic cathedral, role in French coronations, and significance during both World Wars.
-
C.
Amiens
Amiens is a historic city in northern France, known for its Gothic cathedral and role as the site of the 1802 Treaty of Amiens.
-
D.
Bourges
Bourges is a historic city in central France known for its well-preserved medieval architecture and its UNESCO-listed Gothic cathedral, Saint-Étienne.
-
E.
Tournus
Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
- 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_69a886023194819080a3fccd6e325d0e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a909cf3c7481909ddbe6a6596bb0c8 |
completed | March 5, 2026, 4:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69af9040c20c8190aaae6f22fc893032 |
completed | March 10, 2026, 3:30 a.m. |
Created at: March 4, 2026, 7:28 p.m.