Triple
T16596471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Val-d'Illiez |
E403219
|
entity |
| Predicate | hasLocality |
P7943
|
FINISHED |
| Object | Champoussin |
E1211220
|
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: Champoussin | Statement: [Val-d'Illiez, hasLocality, Champoussin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Champoussin Context triple: [Val-d'Illiez, hasLocality, Champoussin]
-
A.
Champoussin
chosen
Champoussin is a small Swiss alpine village and ski resort that forms part of the Portes du Soleil ski area in the Valais region.
-
B.
Verger
Verger is a surname most notably associated with Mason Verger, a wealthy and sadistic antagonist in Thomas Harris’s Hannibal Lecter series.
-
C.
Parmys
Parmys was an Achaemenid Persian noblewoman and princess, known as a granddaughter of Cyrus the Great and a queen consort during the reign of Darius I.
-
D.
Mirepoix
Mirepoix is a medieval bastide town in southwestern France known for its picturesque half-timbered houses and arcaded central square.
-
E.
Malherbe
Malherbe is the commonly used nickname for the French football club Stade Malherbe Caen.
- 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_69d883880d0c81908b5fcd454e767b60 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35d723c508190b5afbda5eec5abea |
completed | April 18, 2026, 10:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00759fe6ec81908c5321dcba558269 |
completed | May 10, 2026, 12:10 p.m. |
Created at: April 10, 2026, 5:16 a.m.