Triple

T14424635
Position Surface form Disambiguated ID Type / Status
Subject Saint-Vincent-de-Paul, Paris E357663 entity
Predicate hasNearbyMetroStation P26735 FINISHED
Object Poissonnière (Paris Métro)
Poissonnière is a Paris Métro station on Line 7 located in the 10th arrondissement of Paris.
 E1099244 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: Poissonnière (Paris Métro) | Statement: [Saint-Vincent-de-Paul, Paris, hasNearbyMetroStation, Poissonnière (Paris Métro)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Poissonnière (Paris Métro)
Context triple: [Saint-Vincent-de-Paul, Paris, hasNearbyMetroStation, Poissonnière (Paris Métro)]
  • A. Pigalle (Paris Métro)
    Pigalle (Paris Métro) is a Paris underground railway station serving lines 2 and 12 in the lively Pigalle district near Montmartre.
  • B. Picpus (Paris Métro)
    Picpus (Paris Métro) is a station on Line 6 of the Paris Métro located in the 12th arrondissement of Paris.
  • C. Pont Neuf (Paris Métro)
    Pont Neuf is a Paris Métro station on Line 7 located near the historic Pont Neuf bridge and the Right Bank of the Seine in central Paris.
  • D. Boissière (Paris Métro)
    Boissière (Paris Métro) is a Paris Métro station in the 16th arrondissement, serving Line 6 near the Trocadéro area.
  • E. Pont de Neuilly (Paris Métro)
    Pont de Neuilly (Paris Métro) is a station on Line 1 of the Paris Métro serving the Neuilly-sur-Seine area just west of central Paris.
  • 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: Poissonnière (Paris Métro)
Triple: [Saint-Vincent-de-Paul, Paris, hasNearbyMetroStation, Poissonnière (Paris Métro)]
Generated description
Poissonnière is a Paris Métro station on Line 7 located in the 10th arrondissement of Paris.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Poissonnière (Paris Métro)
Target entity description: Poissonnière is a Paris Métro station on Line 7 located in the 10th arrondissement of Paris.
  • A. Pigalle (Paris Métro)
    Pigalle (Paris Métro) is a Paris underground railway station serving lines 2 and 12 in the lively Pigalle district near Montmartre.
  • B. Picpus (Paris Métro)
    Picpus (Paris Métro) is a station on Line 6 of the Paris Métro located in the 12th arrondissement of Paris.
  • C. Pont Neuf (Paris Métro)
    Pont Neuf is a Paris Métro station on Line 7 located near the historic Pont Neuf bridge and the Right Bank of the Seine in central Paris.
  • D. Boissière (Paris Métro)
    Boissière (Paris Métro) is a Paris Métro station in the 16th arrondissement, serving Line 6 near the Trocadéro area.
  • E. Pont de Neuilly (Paris Métro)
    Pont de Neuilly (Paris Métro) is a station on Line 1 of the Paris Métro serving the Neuilly-sur-Seine area just west of central Paris.
  • 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_69d8279402a88190821ffa39ae15bccf completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de91123f848190ba3fb18a76c2d24c completed April 14, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bcd2a908190ad7d5ebf11b41551 completed May 8, 2026, 3:43 a.m.
NEDg Description generation batch_69fd5d585cc08190908bc5f9b8abdb82 completed May 8, 2026, 3:49 a.m.
NED2 Entity disambiguation (via description) batch_69fd5e0bbd6c8190b14039b3335692c7 completed May 8, 2026, 3:52 a.m.
Created at: April 10, 2026, 1:18 a.m.