Triple

T19458221
Position Surface form Disambiguated ID Type / Status
Subject Cachan E486790 entity
Predicate hasEducationalInstitution P113 FINISHED
Object École Spéciale des Travaux Publics NE NERFINISHED

How this triple was built (3 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: École Spéciale des Travaux Publics | Statement: [Cachan, hasEducationalInstitution, École Spéciale des Travaux Publics]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: École Spéciale des Travaux Publics
Context triple: [Cachan, hasEducationalInstitution, École Spéciale des Travaux Publics]
  • A. École des Ponts et Chaussées
    École des Ponts et Chaussées is one of France’s oldest and most prestigious engineering schools, renowned for training civil engineers and leaders in infrastructure, transportation, and environmental engineering.
  • B. École Nationale des Travaux Publics de l'État
    École Nationale des Travaux Publics de l'État is a prestigious French grande école specializing in civil engineering and public works, training high-level engineers and officials for infrastructure and territorial development.
  • C. École des Ingénieurs de la Ville de Paris
    École des Ingénieurs de la Ville de Paris was a prestigious French engineering school specializing in urban engineering and public works, particularly for the City of Paris.
  • D. École nationale supérieure d’arts et métiers
    École nationale supérieure d’arts et métiers is a prestigious French grande école specializing in engineering and industrial technologies, known for training high-level engineers and technical leaders.
  • E. École Centrale des Arts et Manufactures
    École Centrale des Arts et Manufactures is a prestigious French engineering grande école renowned for training leading industrial and civil engineers.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: École Spéciale des Travaux Publics
Target entity description: École Spéciale des Travaux Publics is a renowned French engineering school specializing in civil engineering, construction, and public works.
  • A. École des Ponts et Chaussées
    École des Ponts et Chaussées is one of France’s oldest and most prestigious engineering schools, renowned for training civil engineers and leaders in infrastructure, transportation, and environmental engineering.
  • B. École Nationale des Travaux Publics de l'État
    École Nationale des Travaux Publics de l'État is a prestigious French grande école specializing in civil engineering and public works, training high-level engineers and officials for infrastructure and territorial development.
  • C. École des Ingénieurs de la Ville de Paris
    École des Ingénieurs de la Ville de Paris was a prestigious French engineering school specializing in urban engineering and public works, particularly for the City of Paris.
  • D. École nationale supérieure d’arts et métiers
    École nationale supérieure d’arts et métiers is a prestigious French grande école specializing in engineering and industrial technologies, known for training high-level engineers and technical leaders.
  • E. École Centrale des Arts et Manufactures
    École Centrale des Arts et Manufactures is a prestigious French engineering grande école renowned for training leading industrial and civil engineers.
  • F. None of above. chosen

Provenance (2 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_69d8e8d86d608190bd199a98d0297f27 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e633c569a081908b5a71226345a929 completed April 20, 2026, 2:10 p.m.
Created at: April 10, 2026, 1:38 p.m.