Triple
T2135560
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chambéry |
E46643
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Ouahigouya |
E235867
|
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: Ouahigouya | Statement: [Chambéry, hasTwinTown, Ouahigouya]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ouahigouya Context triple: [Chambéry, hasTwinTown, Ouahigouya]
-
A.
Ouahigouya
chosen
Ouahigouya is a major city in northern Burkina Faso known as an important commercial and administrative center of the region.
-
B.
Riobamba
Riobamba is a city in the central highlands of Ecuador, known as a gateway to the Andes and nearby Chimborazo volcano.
-
C.
Caparrapí
Caparrapí is a municipality in central Colombia known for its rural character and location within the Andean region of the Cundinamarca Department.
-
D.
Combarbalá
Combarbalá is a small Chilean town and municipality in the Coquimbo Region, known for its semi-arid landscapes, goat farming, and distinctive combarbalite stone crafts.
-
E.
Guayaramerín
Guayaramerín is a Bolivian town and river port in the Beni Department, located on the Mamoré River near the border with Brazil.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbdc4ce8c81908d143d5451681e6a |
completed | March 7, 2026, 5:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58d3275481909c8d74ca7c037ddd |
completed | March 9, 2026, 5:21 a.m. |
Created at: March 4, 2026, 7:44 p.m.