Triple

T13693523
Position Surface form Disambiguated ID Type / Status
Subject Pierre Savoye E328326 entity
Predicate employer P7 FINISHED
Object L’Union
L’Union is a French regional newspaper known for covering local and national news in the Champagne-Ardenne and surrounding areas.
E1054353 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: L’Union | Statement: [Pierre Savoye, employer, L’Union]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: L’Union
Context triple: [Pierre Savoye, employer, L’Union]
  • A. La Union
    La Union is a coastal province in the Ilocos Region of the Philippines known for its Ilocano heritage, surfing beaches, and emerging tourism industry.
  • B. French Union
    The French Union was a political entity established after World War II to reorganize France’s relationship with its colonies and overseas territories within a quasi-federal framework.
  • C. Francie
    Francie is a diminutive given name, typically used as a nickname for Francis or Frances.
  • D. Arpitanie
    Arpitanie is a cultural and linguistic region in parts of France, Switzerland, and Italy where the Arpitan (Franco-Provençal) language and related traditions are historically rooted.
  • E. Libé
    Libé is the common nickname for Libération, a prominent French daily newspaper known for its left-leaning, progressive editorial stance.
  • 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: L’Union
Triple: [Pierre Savoye, employer, L’Union]
Generated description
L’Union is a French regional newspaper known for covering local and national news in the Champagne-Ardenne and surrounding areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: L’Union
Target entity description: L’Union is a French regional newspaper known for covering local and national news in the Champagne-Ardenne and surrounding areas.
  • A. La Union
    La Union is a coastal province in the Ilocos Region of the Philippines known for its Ilocano heritage, surfing beaches, and emerging tourism industry.
  • B. French Union
    The French Union was a political entity established after World War II to reorganize France’s relationship with its colonies and overseas territories within a quasi-federal framework.
  • C. Francie
    Francie is a diminutive given name, typically used as a nickname for Francis or Frances.
  • D. Arpitanie
    Arpitanie is a cultural and linguistic region in parts of France, Switzerland, and Italy where the Arpitan (Franco-Provençal) language and related traditions are historically rooted.
  • E. Libé
    Libé is the common nickname for Libération, a prominent French daily newspaper known for its left-leaning, progressive editorial stance.
  • 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_69d8076ff62081908a7bd79889edd7a0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc8757b648190a26181efbad09a43 completed April 12, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69f7944e7ea0819098a9fbf8842d314b completed May 3, 2026, 6:30 p.m.
NEDg Description generation batch_69f79715571081909c1177a3fd09b4d5 completed May 3, 2026, 6:42 p.m.
NED2 Entity disambiguation (via description) batch_69f797caabfc8190844e6b7d8125aeb6 completed May 3, 2026, 6:45 p.m.
Created at: April 9, 2026, 9:54 p.m.