Triple
T9732243
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Line 3 |
E235772
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object | Saint-Lazare |
E211473
|
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: Saint-Lazare | Statement: [Paris Métro Line 3, hasStation, Saint-Lazare]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Lazare Context triple: [Paris Métro Line 3, hasStation, Saint-Lazare]
-
A.
Saint-Lazare
chosen
Saint-Lazare is one of Paris’s busiest transport hubs, serving as a major Métro interchange connected to the Gare Saint-Lazare railway station.
-
B.
Saint-Lazare Cathedral
Saint-Lazare Cathedral is a Romanesque Catholic cathedral in Autun, France, renowned for its 12th-century sculptural decoration, especially the Last Judgment tympanum by Gislebertus.
-
C.
Invalides
Invalides is a Paris Métro and RER station located near Les Invalides in central Paris, serving as a key transport hub for the surrounding historic and governmental district.
-
D.
Saint-Philippe du Roule
Saint-Philippe du Roule is a Paris Métro station in the 8th arrondissement, serving the upscale district near the Champs-Élysées.
-
E.
La Part-Dieu
La Part-Dieu is a major business and commercial district in Lyon, France, known for its large shopping center, office towers, and central train station.
- 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_69ca84d0fad481909cdd45aa77416c48 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cd9eb3d6e4819090b3c7fb92550c57 |
completed | April 1, 2026, 10:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d19fbbba2081909a15725a68423162 |
completed | April 4, 2026, 11:33 p.m. |
Created at: March 30, 2026, 8:22 p.m.