Triple

T3167285
Position Surface form Disambiguated ID Type / Status
Subject Conférence des grandes écoles E66241 entity
Predicate shortName P43 FINISHED
Object CGE
CGE is a French association that brings together the country’s leading grandes écoles, representing elite higher education and research institutions.
 E334048 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: CGE | Statement: [Conférence des grandes écoles, shortName, CGE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: CGE
Context triple: [Conférence des grandes écoles, shortName, CGE]
  • A. GBE
    GBE is the highest grade of the Order of the British Empire, typically awarded for exceptionally distinguished service to the arts, sciences, public services, or charitable work.
  • B. GEOC
    GEOC is the commonly used abbreviation for the Division of Geochemistry, a professional group focused on the study of the chemical composition and processes of the Earth.
  • C. GSE
    GSE is the abbreviation commonly used for the Stanford Graduate School of Education, a leading institution for research and training in education.
  • D. CH-GE
    CH-GE is the ISO 3166-2 code representing the Canton of Geneva in Switzerland.
  • E. GPCE
    GPCE (Generative Programming: Concepts & Experiences) is an academic conference focused on research in generative software development, program transformation, and related programming language technologies.
  • 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: CGE
Triple: [Conférence des grandes écoles, shortName, CGE]
Generated description
CGE is a French association that brings together the country’s leading grandes écoles, representing elite higher education and research institutions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: CGE
Target entity description: CGE is a French association that brings together the country’s leading grandes écoles, representing elite higher education and research institutions.
  • A. GBE
    GBE is the highest grade of the Order of the British Empire, typically awarded for exceptionally distinguished service to the arts, sciences, public services, or charitable work.
  • B. GEOC
    GEOC is the commonly used abbreviation for the Division of Geochemistry, a professional group focused on the study of the chemical composition and processes of the Earth.
  • C. GSE
    GSE is the abbreviation commonly used for the Stanford Graduate School of Education, a leading institution for research and training in education.
  • D. CH-GE
    CH-GE is the ISO 3166-2 code representing the Canton of Geneva in Switzerland.
  • E. GPCE
    GPCE (Generative Programming: Concepts & Experiences) is an academic conference focused on research in generative software development, program transformation, and related programming language technologies.
  • 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_69ad8585d7988190af37365331093ccd completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6457acc8190b2b9acbd1cfcdb91 completed March 8, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b235e108cc81909d5733bd00cb0bee completed March 12, 2026, 3:41 a.m.
NEDg Description generation batch_69b2372a54a481908a4a954b8986aad7 completed March 12, 2026, 3:46 a.m.
NED2 Entity disambiguation (via description) batch_69b23806a3c8819096069982b3612730 completed March 12, 2026, 3:50 a.m.
Created at: March 8, 2026, 3:06 p.m.