Triple
T14219728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chōfu |
E352456
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Lévis |
E338471
|
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: Lévis | Statement: [Chōfu, hasSisterCity, Lévis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lévis Context triple: [Chōfu, hasSisterCity, Lévis]
-
A.
Lévis
chosen
Lévis is a city located on the south shore of the St. Lawrence River in Quebec, Canada, directly across from Quebec City.
-
B.
Trois-Rivières
Trois-Rivières is a historic industrial and cultural city in the Canadian province of Quebec, located roughly midway between Montreal and Quebec City.
-
C.
Bécancour
Bécancour is a small industrial and agricultural city in the Centre-du-Québec region of Quebec, Canada, located along the south shore of the Saint Lawrence River.
-
D.
Rimouski
Rimouski is a city in eastern Quebec, Canada, located along the south shore of the Saint Lawrence River and known as a regional center for education, research, and maritime activities.
-
E.
Verchères
Verchères is a riverside municipality in Quebec, Canada, located on the south shore of the Saint Lawrence River and known for its historic village and agricultural surroundings.
- 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_69d8278a06e481908b5d6af0a8afe737 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de621258d4819085f358cd2cf109e4 |
completed | April 14, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd949df6688190ac92f7e0945bce02 |
completed | May 8, 2026, 7:45 a.m. |
Created at: April 10, 2026, 1:06 a.m.