Triple
T790600
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jura |
E16904
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Delémont |
E161079
|
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: Delémont | Statement: [Jura, capital, Delémont]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Delémont Context triple: [Jura, capital, Delémont]
-
A.
Delémont
chosen
Delémont is a historic town in northwestern Switzerland that serves as the capital of the canton of Jura.
-
B.
Hermance
Hermance is a small lakeside municipality on the shores of Lake Geneva in southwestern Switzerland.
-
C.
Martigny
Martigny is a historic town in southwestern Switzerland known as a cultural and transportation hub in the canton of Valais, near the Great St. Bernard Pass.
-
D.
Cluses
Cluses is a small industrial town in southeastern France known for its precision engineering and watchmaking heritage, located in the Arve Valley of the Haute-Savoie department in the Alps.
-
E.
Bardonnex
Bardonnex is a small Swiss municipality located in the canton of Geneva, near the country’s border with France.
- 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_69a4936cb7448190914f5fe4b8d81607 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a79754988190ab494b1c54d6a2a4 |
completed | March 1, 2026, 8:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad0132cd6081908d70112213343063 |
completed | March 8, 2026, 4:55 a.m. |
Created at: March 1, 2026, 7:38 p.m.