Triple
T12002093
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thurgau |
E285688
|
entity |
| Predicate | hasMunicipality |
P847
|
FINISHED |
| Object | Romanshorn |
E524736
|
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: Romanshorn | Statement: [Thurgau, hasMunicipality, Romanshorn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romanshorn Context triple: [Thurgau, hasMunicipality, Romanshorn]
-
A.
Romanshorn
chosen
Romanshorn is a Swiss town on the southern shore of Lake Constance, known as an important regional transport hub and ferry port.
-
B.
Ramiswil
Ramiswil is a small rural municipality in the canton of Solothurn in northwestern Switzerland, known for its scenic Jura landscape and agricultural character.
-
C.
Grenchen
Grenchen is a Swiss town in the canton of Solothurn known for its watchmaking industry and location at the foot of the Jura Mountains.
-
D.
Hergiswil
Hergiswil is a Swiss lakeside municipality known for its scenic setting on Lake Lucerne and its historic glassworks.
-
E.
Landquart
Landquart is a river in eastern Switzerland that flows through the canton of Graubünden before joining the Alpine Rhine.
- 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_69d6ab45a368819084fce08bf0dc3705 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c36b248190b446b17def94885b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64b8062f88190bdb644a8e0b1ac5f |
completed | May 2, 2026, 7:07 p.m. |
Created at: April 8, 2026, 9:46 p.m.