Triple
T13842078
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Précy-sur-Marne |
E332682
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Lesches |
E332972
|
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: Lesches | Statement: [Précy-sur-Marne, sharesBorderWith, Lesches]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lesches Context triple: [Précy-sur-Marne, sharesBorderWith, Lesches]
-
A.
Lesches
chosen
Lesches is a small French commune located in the Seine-et-Marne department in the Île-de-France region, near Paris.
-
B.
Tuchan
Tuchan is a small commune in southern France’s Aude department, known for its wine production and scenic location in the Corbières hills.
-
C.
Larche
Larche is a small village in the French Alps near the Italian border, known as a gateway to the surrounding mountain passes and hiking routes.
-
D.
Larche
Larche is a commune in the Corrèze department of south-central France, situated within the Brive-la-Gaillarde area.
-
E.
Leppe
Leppe is a small river in western Germany that flows through the hilly Bergisches Land region of North Rhine-Westphalia.
- 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_69d81c5ba13c8190839315f54768acfd |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02afce788190a74dce4e6a3569fa |
completed | April 14, 2026, 9:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8f630d081909439e1cdc5d60430 |
completed | May 3, 2026, 9:07 p.m. |
Created at: April 9, 2026, 10:13 p.m.