Triple

T8689890
Position Surface form Disambiguated ID Type / Status
Subject Porte d’Orléans E206258 entity
Predicate hasAdjacentStationNorth P32736 FINISHED
Object Alésia (Paris Métro)
Alésia is a Paris Métro station on Line 4 located in the 14th arrondissement, serving the Place d'Alésia area.
 E750637 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: Alésia (Paris Métro) | Statement: [Porte d’Orléans, hasAdjacentStationNorth, Alésia (Paris Métro)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alésia (Paris Métro)
Context triple: [Porte d’Orléans, hasAdjacentStationNorth, Alésia (Paris Métro)]
  • A. Kléber (Paris Métro)
    Kléber (Paris Métro) is a Paris Métro station on Line 6 located near the Arc de Triomphe in the 16th arrondissement.
  • B. Boissière (Paris Métro)
    Boissière (Paris Métro) is a Paris Métro station in the 16th arrondissement, serving Line 6 near the Trocadéro area.
  • C. Saint-Ambroise (Paris Métro)
    Saint-Ambroise is a Paris Métro station in the 11th arrondissement, serving Line 9 near the Église Saint-Ambroise.
  • D. Falguière (Paris Métro)
    Falguière is a Paris Métro station on Line 12 located in the 15th arrondissement near Montparnasse.
  • E. Bir-Hakeim (Paris Métro)
    Bir-Hakeim is a Paris Métro station on Line 6, notable for its elevated tracks and proximity to the Eiffel Tower.
  • 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: Alésia (Paris Métro)
Triple: [Porte d’Orléans, hasAdjacentStationNorth, Alésia (Paris Métro)]
Generated description
Alésia is a Paris Métro station on Line 4 located in the 14th arrondissement, serving the Place d'Alésia area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alésia (Paris Métro)
Target entity description: Alésia is a Paris Métro station on Line 4 located in the 14th arrondissement, serving the Place d'Alésia area.
  • A. Kléber (Paris Métro)
    Kléber (Paris Métro) is a Paris Métro station on Line 6 located near the Arc de Triomphe in the 16th arrondissement.
  • B. Boissière (Paris Métro)
    Boissière (Paris Métro) is a Paris Métro station in the 16th arrondissement, serving Line 6 near the Trocadéro area.
  • C. Saint-Ambroise (Paris Métro)
    Saint-Ambroise is a Paris Métro station in the 11th arrondissement, serving Line 9 near the Église Saint-Ambroise.
  • D. Falguière (Paris Métro)
    Falguière is a Paris Métro station on Line 12 located in the 15th arrondissement near Montparnasse.
  • E. Bir-Hakeim (Paris Métro)
    Bir-Hakeim is a Paris Métro station on Line 6, notable for its elevated tracks and proximity to the Eiffel Tower.
  • 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_69ca835481fc819084e33d3bc883bfa6 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc5734602c81909a0687e00f4a4a26 completed March 31, 2026, 11:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef3df73b88190b67138ee5129de8b completed April 2, 2026, 10:55 p.m.
NEDg Description generation batch_69cef52200788190a8173da1aaa4f681 completed April 2, 2026, 11 p.m.
NED2 Entity disambiguation (via description) batch_69cef6c109b08190bb29ce2747f3ccb7 completed April 2, 2026, 11:07 p.m.
Created at: March 30, 2026, 6:33 p.m.