Triple
T8844820
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue de Compiègne |
E210477
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Rue de Dunkerque |
E37922
|
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: Rue de Dunkerque | Statement: [Rue de Compiègne, near, Rue de Dunkerque]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rue de Dunkerque Context triple: [Rue de Compiègne, near, Rue de Dunkerque]
-
A.
Rue de Dunkerque
chosen
Rue de Dunkerque is a major street in Paris’s 10th arrondissement, best known for running alongside and providing access to the Gare du Nord railway station.
-
B.
Rue de Maubeuge
Rue de Maubeuge is a street in Paris, France, known for its proximity to major railway stations like Gare du Nord and its typical Haussmann-era urban architecture.
-
C.
Rue de Lille
Rue de Lille is a notable street in Paris’s 7th arrondissement, running parallel to the Seine and known for its historic buildings and cultural institutions.
-
D.
Rue de Saint-Quentin
Rue de Saint-Quentin is a street in Paris, France, located near major railway stations in the 10th arrondissement.
-
E.
Rue de Compiègne
Rue de Compiègne is a street in Paris, France, located near Rue de Dunkerque in the area around Gare du Nord.
- 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_69ca838967bc8190b46c3c80a2887ea4 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc60a6623c8190ba43545544f58633 |
completed | April 1, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de54a30b748190bb791078e9dde442 |
completed | April 14, 2026, 2:52 p.m. |
Created at: March 30, 2026, 6:48 p.m.