Triple

T16340824
Position Surface form Disambiguated ID Type / Status
Subject Vanves E396795 entity
Predicate hasSportsFacility P105 FINISHED
Object Stade de Vanves
Stade de Vanves is a local multi-sport stadium and athletic complex serving the community of Vanves, a suburb just outside Paris, France.
E1215588 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: Stade de Vanves | Statement: [Vanves, hasSportsFacility, Stade de Vanves]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Stade de Vanves
Context triple: [Vanves, hasSportsFacility, Stade de Vanves]
  • A. Stade Pierre Duboeuf
    Stade Pierre Duboeuf is a multi-use sports stadium located in Bron, France, primarily hosting football matches and local athletic events.
  • B. Stade François-Coty
    Stade François-Coty is a football stadium in Ajaccio, Corsica, best known as the home ground of French club AC Ajaccio.
  • C. Stade Jean-Bouin
    Stade Jean-Bouin is a rugby stadium in Paris, France, best known as the home venue of the Stade Français rugby union club.
  • D. Stade Malleval
    Stade Malleval is a sports stadium in Roanne, France, primarily used for football and other local sporting events.
  • E. Stade Yves-du-Manoir
    Stade Yves-du-Manoir is a multi-purpose sports stadium in Montpellier, France, best known as the home ground of the Montpellier Hérault Rugby club.
  • 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: Stade de Vanves
Triple: [Vanves, hasSportsFacility, Stade de Vanves]
Generated description
Stade de Vanves is a local multi-sport stadium and athletic complex serving the community of Vanves, a suburb just outside Paris, France.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Stade de Vanves
Target entity description: Stade de Vanves is a local multi-sport stadium and athletic complex serving the community of Vanves, a suburb just outside Paris, France.
  • A. Stade Pierre Duboeuf
    Stade Pierre Duboeuf is a multi-use sports stadium located in Bron, France, primarily hosting football matches and local athletic events.
  • B. Stade François-Coty
    Stade François-Coty is a football stadium in Ajaccio, Corsica, best known as the home ground of French club AC Ajaccio.
  • C. Stade Jean-Bouin
    Stade Jean-Bouin is a rugby stadium in Paris, France, best known as the home venue of the Stade Français rugby union club.
  • D. Stade Malleval
    Stade Malleval is a sports stadium in Roanne, France, primarily used for football and other local sporting events.
  • E. Stade Yves-du-Manoir
    Stade Yves-du-Manoir is a multi-purpose sports stadium in Montpellier, France, best known as the home ground of the Montpellier Hérault Rugby club.
  • 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_69d87f26864c819088365ca381a003c2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2da09dcf48190b6fdd14b1812c56a completed April 18, 2026, 1:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f3f93348190b835218ae42f3463 completed May 10, 2026, 9:26 a.m.
NEDg Description generation batch_6a0050e566c48190ab8560e2f1f4173b completed May 10, 2026, 9:33 a.m.
NED2 Entity disambiguation (via description) batch_6a00533c74748190af6477d9e86cbc63 completed May 10, 2026, 9:43 a.m.
Created at: April 10, 2026, 5:07 a.m.