Triple
T1040646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romansh language |
E22461
|
entity |
| Predicate | hasRegulator |
P4784
|
FINISHED |
| Object |
Lia Rumantscha
Lia Rumantscha is the main organization dedicated to promoting, standardizing, and preserving the Romansh language in Switzerland.
|
E125614
|
NE FINISHED |
How this triple was built (4 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: Lia Rumantscha | Statement: [Romansh language, hasRegulator, Lia Rumantscha]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lia Rumantscha Context triple: [Romansh language, hasRegulator, Lia Rumantscha]
-
A.
Berner
A Berner is a resident or native of the Swiss city of Bern.
-
B.
Romandy
Romandy is the French-speaking western region of Switzerland, encompassing cantons such as Geneva, Vaud, Neuchâtel, and Jura.
-
C.
Aosta Valley
Aosta Valley is a mountainous autonomous region in northwestern Italy, renowned for its Alpine landscapes, ski resorts, and proximity to major peaks such as Mont Blanc.
-
D.
Nyon District
Nyon District is an administrative district in the canton of Vaud in western Switzerland, situated along Lake Geneva and functioning as part of the broader Geneva metropolitan region.
-
E.
Swabian Jura
The Swabian Jura is a low mountain range in southwestern Germany known for its limestone plateaus, caves, and picturesque landscapes stretching across Baden-Württemberg.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lia Rumantscha Triple: [Romansh language, hasRegulator, Lia Rumantscha]
Generated description
Lia Rumantscha is the main organization dedicated to promoting, standardizing, and preserving the Romansh language in Switzerland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lia Rumantscha Target entity description: Lia Rumantscha is the main organization dedicated to promoting, standardizing, and preserving the Romansh language in Switzerland.
-
A.
Berner
A Berner is a resident or native of the Swiss city of Bern.
-
B.
Romandy
Romandy is the French-speaking western region of Switzerland, encompassing cantons such as Geneva, Vaud, Neuchâtel, and Jura.
-
C.
Aosta Valley
Aosta Valley is a mountainous autonomous region in northwestern Italy, renowned for its Alpine landscapes, ski resorts, and proximity to major peaks such as Mont Blanc.
-
D.
Nyon District
Nyon District is an administrative district in the canton of Vaud in western Switzerland, situated along Lake Geneva and functioning as part of the broader Geneva metropolitan region.
-
E.
Swabian Jura
The Swabian Jura is a low mountain range in southwestern Germany known for its limestone plateaus, caves, and picturesque landscapes stretching across Baden-Württemberg.
- F. None of above. chosen
Provenance (5 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_69a493d91478819094cc01fb65564bc1 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b82e4d2c81909ca1264852baf04d |
completed | March 1, 2026, 10:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac4c18692c819092e1045199053a39 |
completed | March 7, 2026, 4:02 p.m. |
| NEDg | Description generation | batch_69ac4ca07ce88190bfbf959adc84a74e |
completed | March 7, 2026, 4:04 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac4d3f62c881908e189bfe8cbbd2ac |
completed | March 7, 2026, 4:07 p.m. |
Created at: March 1, 2026, 7:41 p.m.