Triple
T17985031
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Göschenen |
E430208
|
entity |
| Predicate | connectsByRailTo |
P13914
|
FINISHED |
| Object | Erstfeld |
—
|
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: Erstfeld | Statement: [Göschenen, connectsByRailTo, Erstfeld]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erstfeld Context triple: [Göschenen, connectsByRailTo, Erstfeld]
-
A.
Erstfeld
chosen
Erstfeld is a municipality in the Swiss canton of Uri, situated in a mountainous valley that serves as an important transport corridor through the Alps.
-
B.
Lülsfeld
Lülsfeld is a small municipality in the Schweinfurt district of Lower Franconia in northern Bavaria, Germany.
-
C.
Birkenfeld
Birkenfeld is a town in western Germany historically associated with the Palatine counts, including Christian I of Birkenfeld-Zweibrücken.
-
D.
Lauterhofen
Lauterhofen is a market town in Bavaria, Germany, known for its rural character and location within the Upper Palatinate region.
-
E.
Odelzhausen
Odelzhausen is a municipality in Bavaria, Germany, known for its historic castle and location along the Autobahn between Munich and Augsburg.
- 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_69d8b90364248190a37381adea932f42 |
completed | April 10, 2026, 8:46 a.m. |
| NER | Named-entity recognition | batch_69e4b29a27b081909a128a6b978eabf8 |
completed | April 19, 2026, 10:46 a.m. |
Created at: April 10, 2026, 10:23 a.m.