Triple
T8883704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Line 4 (Paris Métro) |
E211472
|
entity |
| Predicate | hasStation |
P35
|
FINISHED |
| Object |
Marcadet–Poissonniers
Marcadet–Poissonniers is a Paris Métro station in the 18th arrondissement that serves as an interchange between lines 4 and 12.
|
E765955
|
NE FINISHED |
How this triple was built (4 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: Marcadet–Poissonniers | Statement: [Line 4 (Paris Métro), hasStation, Marcadet–Poissonniers]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcadet–Poissonniers Context triple: [Line 4 (Paris Métro), hasStation, Marcadet–Poissonniers]
-
A.
Marche-les-Dames
Marche-les-Dames is a village in the Namur province of Belgium, best known as the site where King Albert I died in a mountaineering accident.
-
B.
Orléat
Orléat is a small commune in central France’s Puy-de-Dôme department, known for its rural character within the Auvergne region.
-
C.
Pontarlier
Pontarlier is a historic town in eastern France near the Swiss border, known for its role in the absinthe industry and its location in the Jura Mountains.
-
D.
Hurepoix
Hurepoix is a historic region of northern France, southwest of Paris, known for its rural landscapes and small towns such as Dourdan.
-
E.
Boussy-Saint-Antoine
Boussy-Saint-Antoine is a suburban commune in the Essonne department in the Île-de-France region of northern France.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marcadet–Poissonniers Triple: [Line 4 (Paris Métro), hasStation, Marcadet–Poissonniers]
Generated description
Marcadet–Poissonniers is a Paris Métro station in the 18th arrondissement that serves as an interchange between lines 4 and 12.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marcadet–Poissonniers Target entity description: Marcadet–Poissonniers is a Paris Métro station in the 18th arrondissement that serves as an interchange between lines 4 and 12.
-
A.
Marche-les-Dames
Marche-les-Dames is a village in the Namur province of Belgium, best known as the site where King Albert I died in a mountaineering accident.
-
B.
Orléat
Orléat is a small commune in central France’s Puy-de-Dôme department, known for its rural character within the Auvergne region.
-
C.
Pontarlier
Pontarlier is a historic town in eastern France near the Swiss border, known for its role in the absinthe industry and its location in the Jura Mountains.
-
D.
Hurepoix
Hurepoix is a historic region of northern France, southwest of Paris, known for its rural landscapes and small towns such as Dourdan.
-
E.
Boussy-Saint-Antoine
Boussy-Saint-Antoine is a suburban commune in the Essonne department in the Île-de-France region of northern France.
- F. None of above. chosen
Provenance (5 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_69ca838f9e20819096ab1f236a70381a |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc616b2d988190b923ef1e33aab787 |
completed | April 1, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfba1b1bec8190ab667a0c5dba3513 |
completed | April 3, 2026, 1:01 p.m. |
| NEDg | Description generation | batch_69cfbbf8ff388190beef5f8f1e6935c6 |
completed | April 3, 2026, 1:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfbc570c28819087bea8058c4b08a9 |
completed | April 3, 2026, 1:10 p.m. |
Created at: March 30, 2026, 6:53 p.m.