Triple
T21324601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lausanne–Villeneuve railway line |
E525715
|
entity |
| Predicate | serves |
P98
|
FINISHED |
| Object | Pully |
—
|
NE NERFINISHED |
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: Pully | Statement: [Lausanne–Villeneuve railway line, serves, Pully]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Pully Context triple: [Lausanne–Villeneuve railway line, serves, Pully]
-
A.
Pully
chosen
Pully is a municipality in the canton of Vaud in western Switzerland, located on the shores of Lake Geneva near Lausanne.
-
B.
Lussy
Lussy is a small municipality in the Glâne District of the canton of Fribourg in western Switzerland.
-
C.
Saignelégier
Saignelégier is a municipality in the Swiss canton of Jura known for its rural landscapes, watchmaking heritage, and the annual Marché-Concours horse festival.
-
D.
Pont-en-Ogoz
Pont-en-Ogoz is a Swiss municipality in the canton of Fribourg, known for its scenic setting on the shores of the Lake of Gruyère and its historic island with castle ruins and a church.
-
E.
Pougny
Pougny is a small French commune, likely located near the Swiss border in the Auvergne-Rhône-Alpes region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b51ad810819098c12392c8e55f6c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e77ed7732c8190a0e7aec6e7cbcef2 |
completed | April 21, 2026, 1:42 p.m. |
Created at: April 16, 2026, 4:40 p.m.