Triple

T8688697
Position Surface form Disambiguated ID Type / Status
Subject Paris Expo Porte de Versailles E206230 entity
Predicate ownedBy P347 FINISHED
Object Viparis
Viparis is a major French company that manages and operates leading convention and exhibition centers in the Paris region.
E752231 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: Viparis | Statement: [Paris Expo Porte de Versailles, ownedBy, Viparis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viparis
Context triple: [Paris Expo Porte de Versailles, ownedBy, Viparis]
  • A. Livadeia
    Livadeia is a town in central Greece, near Mount Parnassus, known historically for the ancient oracle of Trophonius and today as the capital of the regional unit of Boeotia.
  • B. Juvisiens
    Juvisiens are the inhabitants of the French commune of Juvisy-sur-Orge, located in the southern suburbs of Paris.
  • C. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • D. Vianen
    Vianen is a historic Dutch town known for its medieval city center and location near major rivers in the western Netherlands.
  • E. Vaitogi
    Vaitogi is a coastal village on the island of Tutuila in American Samoa, known for its dramatic sea cliffs and traditional Samoan culture.
  • 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: Viparis
Triple: [Paris Expo Porte de Versailles, ownedBy, Viparis]
Generated description
Viparis is a major French company that manages and operates leading convention and exhibition centers in the Paris region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Viparis
Target entity description: Viparis is a major French company that manages and operates leading convention and exhibition centers in the Paris region.
  • A. Livadeia
    Livadeia is a town in central Greece, near Mount Parnassus, known historically for the ancient oracle of Trophonius and today as the capital of the regional unit of Boeotia.
  • B. Juvisiens
    Juvisiens are the inhabitants of the French commune of Juvisy-sur-Orge, located in the southern suburbs of Paris.
  • C. Agenais
    Agenais refers to the inhabitants or natives of Agen, a historic town in southwestern France.
  • D. Vianen
    Vianen is a historic Dutch town known for its medieval city center and location near major rivers in the western Netherlands.
  • E. Vaitogi
    Vaitogi is a coastal village on the island of Tutuila in American Samoa, known for its dramatic sea cliffs and traditional Samoan culture.
  • 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_69cc57334b0c8190903a5a1784e74791 completed March 31, 2026, 11:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69cef3d6904c8190a8456a99dae87bf2 completed April 2, 2026, 10:55 p.m.
NEDg Description generation batch_69cef56df85c81908cb10aa7d80ce358 completed April 2, 2026, 11:02 p.m.
NED2 Entity disambiguation (via description) batch_69cef6757cd8819082ffc32256b0f86c completed April 2, 2026, 11:06 p.m.
Created at: March 30, 2026, 6:33 p.m.