Triple

T14582158
Position Surface form Disambiguated ID Type / Status
Subject Audencia Business School E342219 entity
Predicate acronym P43 FINISHED
Object Audencia
Audencia is a leading French business school based in Nantes, known for its international programs and strong focus on responsible management and sustainability.
E1109103 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: Audencia | Statement: [Audencia Business School, acronym, Audencia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Audencia
Context triple: [Audencia Business School, acronym, Audencia]
  • A. Arcour
    Arcour is a French motorway concession company associated with the Vinci Autoroutes network.
  • B. Audeca
    Audeca was the last king of the Suebic Kingdom in Gallaecia, whose brief reign in the late 6th century ended with the annexation of his realm by the Visigothic Kingdom.
  • C. Fortis
    Fortis is a Latin word meaning "brave" or "strong," commonly recognized today from its use in mottos such as "Semper Fortis."
  • D. Aude
    Aude is a department in southern France known for its historic Cathar castles, medieval city of Carcassonne, and Mediterranean coastline.
  • E. Cartrema
    Cartrema is a small genus of flowering shrubs or small trees in the olive family Oleaceae, native to parts of North America and valued as ornamental plants.
  • 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: Audencia
Triple: [Audencia Business School, acronym, Audencia]
Generated description
Audencia is a leading French business school based in Nantes, known for its international programs and strong focus on responsible management and sustainability.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Audencia
Target entity description: Audencia is a leading French business school based in Nantes, known for its international programs and strong focus on responsible management and sustainability.
  • A. Arcour
    Arcour is a French motorway concession company associated with the Vinci Autoroutes network.
  • B. Audeca
    Audeca was the last king of the Suebic Kingdom in Gallaecia, whose brief reign in the late 6th century ended with the annexation of his realm by the Visigothic Kingdom.
  • C. Fortis
    Fortis is a Latin word meaning "brave" or "strong," commonly recognized today from its use in mottos such as "Semper Fortis."
  • D. Aude
    Aude is a department in southern France known for its historic Cathar castles, medieval city of Carcassonne, and Mediterranean coastline.
  • E. Cartrema
    Cartrema is a small genus of flowering shrubs or small trees in the olive family Oleaceae, native to parts of North America and valued as ornamental plants.
  • 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_69d822ddc0f081909cd8163c7de298cd completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb41e71748190a1deacc819dd26d3 completed April 14, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd94ba235c81909e0408ccf2be9628 completed May 8, 2026, 7:46 a.m.
NEDg Description generation batch_69fd9619f33881908e8d95ef09256d34 completed May 8, 2026, 7:51 a.m.
NED2 Entity disambiguation (via description) batch_69fd96e97ec48190aae9b25ce7154802 completed May 8, 2026, 7:55 a.m.
Created at: April 10, 2026, 1:24 a.m.