Triple
T13842032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fresnes-sur-Marne |
E332681
|
entity |
| Predicate | sharesBorderWith |
P224
|
FINISHED |
| Object | Villeroy |
E332686
|
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: Villeroy | Statement: [Fresnes-sur-Marne, sharesBorderWith, Villeroy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Villeroy Context triple: [Fresnes-sur-Marne, sharesBorderWith, Villeroy]
-
A.
Villeroy
chosen
Villeroy is a small French commune located in the Île-de-France region in north-central France.
-
B.
Villeret
Villeret is a small French commune located in the Aube department in the Grand Est region of northeastern France.
-
C.
Vauvert
Vauvert is a commune in southern France known for its location in the Gard department near the Camargue region.
-
D.
Villeroux
Villeroux is a small village in the municipality of Vaux-sur-Sûre in the Walloon region of Belgium.
-
E.
Drouet
Drouet is a French surname most notably associated with Jean-Baptiste Drouet, the postmaster who helped identify and arrest King Louis XVI during his attempted flight in 1791.
- 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.