Triple

T18262569
Position Surface form Disambiguated ID Type / Status
Subject Université de Lorraine E437398 entity
Predicate hasCampus P116 FINISHED
Object Metz campus NE NERFINISHED

How this triple was built (2 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: Metz campus | Statement: [Université de Lorraine, hasCampus, Metz campus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Metz campus
Context triple: [Université de Lorraine, hasCampus, Metz campus]
  • A. Metz campus
    Metz campus is the European satellite campus of the Georgia Institute of Technology located in Metz, France, offering engineering and study-abroad programs.
  • B. Metz campus chosen
    Metz campus is a major site of the Université de Lorraine located in the city of Metz, hosting a range of academic, research, and student life facilities.
  • C. Strasbourg campus
    Strasbourg campus is a site of the École nationale d'administration located in Strasbourg, France, hosting training and academic activities for future high-level civil servants.
  • D. Reims campus
    Reims campus is one of Sciences Po’s regional undergraduate campuses in France, known for its international programs and focus on European and transatlantic studies.
  • E. Dijon campus
    The Dijon campus is one of Sciences Po’s regional campuses in France, specializing in Central and Eastern European studies within the university’s international undergraduate program.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8b913351c8190932b6a426de04b41 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4ff77882c81909774aefc57ccca3e completed April 19, 2026, 4:14 p.m.
Created at: April 10, 2026, 10:34 a.m.