Triple
T5916488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haute-Marne |
E131592
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Langres |
E110891
|
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: Langres | Statement: [Haute-Marne, contains, Langres]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Langres Context triple: [Haute-Marne, contains, Langres]
-
A.
Langres
chosen
Langres is a historic fortified town in northeastern France known for its well-preserved ramparts and as the birthplace of Enlightenment philosopher Denis Diderot.
-
B.
Saint-Brais
Saint-Brais is a small rural municipality in the canton of Jura in northwestern Switzerland, situated in the Franches-Montagnes district.
-
C.
Tournus
Tournus is a historic town in eastern France’s Burgundy region, known for its Romanesque abbey and riverside setting along the Saône.
-
D.
Cholet
Cholet is a town in western France’s Maine-et-Loire department, known historically for its textile industry and as part of the Pays de la Loire region.
-
E.
Fougères
Fougères is a historic town in Brittany, northwestern France, known for its impressive medieval castle and well-preserved old quarter.
- 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_69c0085a1ed08190a7e9a8b6323fd680 |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c037bcea9c8190a34dc03857e3b80b |
completed | March 22, 2026, 6:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c16e882cdc819082b46b9380c430ad |
completed | March 23, 2026, 4:47 p.m. |
Created at: March 22, 2026, 3:59 p.m.