Triple
T19808211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gaston Berger University |
E475871
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Saint-Louis |
—
|
NE NERFINISHED |
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: Saint-Louis | Statement: [Gaston Berger University, locatedNear, Saint-Louis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Louis Context triple: [Gaston Berger University, locatedNear, Saint-Louis]
-
A.
Saint-Louis
Saint-Louis is a historic French crystal manufacturer renowned for its high-end glassware, lighting, and decorative objects.
-
B.
Saint-Louis
Saint-Louis is a French border town in the Alsace region, adjacent to Basel and known as a key cross-border transit and commuter hub between France, Switzerland, and Germany.
-
C.
Saint-Louis
chosen
Saint-Louis is a historic coastal city in northwestern Senegal that served as a major colonial administrative and trading center in French West Africa.
-
D.
Saint-Louis
Saint-Louis is a coastal commune on the Caribbean island of Marie-Galante, known for its beaches, fishing activities, and traditional Creole character.
-
E.
Place Saint-Louis
Place Saint-Louis is a historic medieval square in Metz, France, known for its arcaded houses and lively cafés.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51bc4208190a1c57d8c5d1b15e4 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65429fec8819091e20908101b50eb |
completed | April 20, 2026, 4:28 p.m. |
Created at: April 10, 2026, 1:49 p.m.