Triple

T11770420
Position Surface form Disambiguated ID Type / Status
Subject Hachette Livre E279881 entity
Predicate subsidiary P258 FINISHED
Object Calmann-Lévy
Calmann-Lévy is a historic French publishing house known for its literary catalog and role in French and European publishing.
 E945725 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: Calmann-Lévy | Statement: [Hachette Livre, subsidiary, Calmann-Lévy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Calmann-Lévy
Context triple: [Hachette Livre, subsidiary, Calmann-Lévy]
  • A. Fond Parisien
    Fond Parisien is a small town in southeastern Haiti near the Dominican border, known for its proximity to Lake Azuei and its role as a local agricultural and trading center.
  • B. Wilmotte
    Wilmotte is the surname of Jean-Michel Wilmotte, a prominent French architect and designer known for his contemporary buildings and urban projects.
  • C. Société Anonyme
    Société Anonyme is a common French corporate structure for large, share-based companies with limited liability and publicly tradable shares.
  • D. Pictet
    Pictet is a prominent Swiss family name historically associated with influential figures in finance, politics, and scholarship.
  • E. Vinci SA
    Vinci SA is a major French multinational concessions and construction company specializing in infrastructure development and management worldwide.
  • 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: Calmann-Lévy
Triple: [Hachette Livre, subsidiary, Calmann-Lévy]
Generated description
Calmann-Lévy is a historic French publishing house known for its literary catalog and role in French and European publishing.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Calmann-Lévy
Target entity description: Calmann-Lévy is a historic French publishing house known for its literary catalog and role in French and European publishing.
  • A. Fond Parisien
    Fond Parisien is a small town in southeastern Haiti near the Dominican border, known for its proximity to Lake Azuei and its role as a local agricultural and trading center.
  • B. Wilmotte
    Wilmotte is the surname of Jean-Michel Wilmotte, a prominent French architect and designer known for his contemporary buildings and urban projects.
  • C. Société Anonyme
    Société Anonyme is a common French corporate structure for large, share-based companies with limited liability and publicly tradable shares.
  • D. Pictet
    Pictet is a prominent Swiss family name historically associated with influential figures in finance, politics, and scholarship.
  • E. Vinci SA
    Vinci SA is a major French multinational concessions and construction company specializing in infrastructure development and management worldwide.
  • 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_69d6ab01d2688190ad8ed6bda487eaa5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a55c9f988190b203b66a28c767ae completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f09086c4ec81908bc8b707a49c3ac2 completed April 28, 2026, 10:48 a.m.
NEDg Description generation batch_69f0bd3cf8308190813003daa8cfba4a completed April 28, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69f0ef02c930819086d139834ad4ed84 completed April 28, 2026, 5:31 p.m.
Created at: April 8, 2026, 9:41 p.m.