Triple

T13589601
Position Surface form Disambiguated ID Type / Status
Subject Institut Henri Poincaré E324658 entity
Predicate hasPart P35 FINISHED
Object Bibliothèque de l’Institut Henri Poincaré
The Bibliothèque de l’Institut Henri Poincaré is a specialized research library in Paris focused on mathematics and theoretical physics, serving scholars and students with extensive scientific collections and resources.
E1049171 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: Bibliothèque de l’Institut Henri Poincaré | Statement: [Institut Henri Poincaré, hasPart, Bibliothèque de l’Institut Henri Poincaré]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bibliothèque de l’Institut Henri Poincaré
Context triple: [Institut Henri Poincaré, hasPart, Bibliothèque de l’Institut Henri Poincaré]
  • A. Bibliothèque de l’Institut de France
    The Bibliothèque de l’Institut de France is a prestigious Parisian research library renowned for its vast collections of manuscripts, rare books, and scholarly works associated with the academies of the Institut de France.
  • B. Bibliothèque de l’École nationale des chartes
    The Bibliothèque de l’École nationale des chartes is a specialized academic library in Paris renowned for its rich collections in history, paleography, archival science, and related disciplines.
  • C. Collège de France library
    The Collège de France library is the research and reference library of the Collège de France in Paris, supporting advanced scholarship across a wide range of academic disciplines.
  • D. Institut Henri Poincaré
    The Institut Henri Poincaré is a renowned French research institute in Paris specializing in mathematics and theoretical physics, serving as a major international center for advanced study and collaboration.
  • E. Bibliothèque de l’INHA
    The Bibliothèque de l’INHA is a major French art history research library in Paris, renowned for its extensive collections on art, archaeology, and visual 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: Bibliothèque de l’Institut Henri Poincaré
Triple: [Institut Henri Poincaré, hasPart, Bibliothèque de l’Institut Henri Poincaré]
Generated description
The Bibliothèque de l’Institut Henri Poincaré is a specialized research library in Paris focused on mathematics and theoretical physics, serving scholars and students with extensive scientific collections and resources.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bibliothèque de l’Institut Henri Poincaré
Target entity description: The Bibliothèque de l’Institut Henri Poincaré is a specialized research library in Paris focused on mathematics and theoretical physics, serving scholars and students with extensive scientific collections and resources.
  • A. Bibliothèque de l’Institut de France
    The Bibliothèque de l’Institut de France is a prestigious Parisian research library renowned for its vast collections of manuscripts, rare books, and scholarly works associated with the academies of the Institut de France.
  • B. Bibliothèque de l’École nationale des chartes
    The Bibliothèque de l’École nationale des chartes is a specialized academic library in Paris renowned for its rich collections in history, paleography, archival science, and related disciplines.
  • C. Collège de France library
    The Collège de France library is the research and reference library of the Collège de France in Paris, supporting advanced scholarship across a wide range of academic disciplines.
  • D. Institut Henri Poincaré
    The Institut Henri Poincaré is a renowned French research institute in Paris specializing in mathematics and theoretical physics, serving as a major international center for advanced study and collaboration.
  • E. Bibliothèque de l’INHA
    The Bibliothèque de l’INHA is a major French art history research library in Paris, renowned for its extensive collections on art, archaeology, and visual 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_69d80769eaf081909d82f44e484d6113 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbb055cc98819091fab597b69e5e3e completed April 12, 2026, 2:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f76bc347b881908267455f3bdd50e8 completed May 3, 2026, 3:37 p.m.
NEDg Description generation batch_69f77642e4b881909915c686a0d6c6fa completed May 3, 2026, 4:22 p.m.
NED2 Entity disambiguation (via description) batch_69f7792110e48190a29b6e89c6ebcc03 completed May 3, 2026, 4:34 p.m.
Created at: April 9, 2026, 9:49 p.m.