Triple
T20378536
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris-Austerlitz |
E497755
|
entity |
| Predicate | formerName |
P65
|
FINISHED |
| Object | Gare d'Orléans |
—
|
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: Gare d'Orléans | Statement: [Paris-Austerlitz, formerName, Gare d'Orléans]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gare d'Orléans Context triple: [Paris-Austerlitz, formerName, Gare d'Orléans]
-
A.
Gare d'Orléans
chosen
Gare d'Orléans is the main railway station serving the city of Orléans in north-central France, providing regional and intercity train connections.
-
B.
Gare des Aubrais-Orléans
Gare des Aubrais-Orléans is a major railway station serving the Orléans area in north-central France, functioning as an important regional and intercity transport hub.
-
C.
Gare de Tours
Gare de Tours is the main railway station serving the city of Tours in central France, acting as a regional and intercity transport hub.
-
D.
Gare de Sens
Gare de Sens is the main railway station serving the town of Sens in north-central France, providing regional and intercity train connections.
-
E.
Bar-sur-Aube station
Bar-sur-Aube station is a regional railway station in the commune of Bar-sur-Aube in northeastern France, serving local and regional passenger rail services.
- 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_69e0b4a5b7908190a972e4e7e698ae94 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678af651c8190b4922294a937e699 |
completed | April 20, 2026, 7:04 p.m. |
Created at: April 16, 2026, 11:27 a.m.