Triple
T7238236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D884 road |
E155285
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Saint-Genis-Pouilly |
E13341
|
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: Saint-Genis-Pouilly | Statement: [D884 road, connectsTo, Saint-Genis-Pouilly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Genis-Pouilly Context triple: [D884 road, connectsTo, Saint-Genis-Pouilly]
-
A.
Saint-Genis-Pouilly
chosen
Saint-Genis-Pouilly is a French commune in the Ain department near the Swiss border, known for its proximity to Geneva and the CERN research center.
-
B.
Saint-Véran
Saint-Véran is a French wine appellation in southern Burgundy known for its high-quality Chardonnay-based white wines.
-
C.
Gueugnon
Gueugnon is a small commune in eastern France known historically for its steel industry and location in the Bourgogne-Franche-Comté region.
-
D.
Beaune
Beaune is a historic town in eastern France renowned as the wine capital of Burgundy and a center of Burgundy’s prestigious vineyards and wine trade.
-
E.
Valtournenche
Valtournenche is a mountain village and commune in Italy’s Aosta Valley, known as a gateway to the Matterhorn and a popular destination for alpine climbing and skiing.
- 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_69c688143bfc81908d4176617735e601 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea368fb88190bd9e991e8b94dac6 |
completed | March 27, 2026, 8:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c802a61718819088cc2d37818af4ca |
completed | March 28, 2026, 4:32 p.m. |
Created at: March 27, 2026, 2:55 p.m.