Triple

T8658610
Position Surface form Disambiguated ID Type / Status
Subject Georges Marchais E205487 entity
Predicate familyName P18 FINISHED
Object Marchais
Marchais is a French surname most notably borne by Georges Marchais, a prominent 20th-century French communist politician.
 E748837 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: Marchais | Statement: [Georges Marchais, familyName, Marchais]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marchais
Context triple: [Georges Marchais, familyName, Marchais]
  • A. Tourangeau
    Tourangeau is the French term for a person from the city of Tours in central France, particularly associated with the historic Touraine region.
  • B. Maurage
    Maurage is a village in the Walloon region of Belgium, forming part of the municipality of La Louvière in the province of Hainaut.
  • C. Kléber
    Kléber is a French tire brand known for producing mid-range, reliable tires for passenger cars and light commercial vehicles.
  • D. Martinet
    Martinet is a French surname most famously borne by Charles Martinet, the longtime voice actor of Nintendo’s Mario.
  • E. Honoré
    Honoré is the given name of the renowned 19th-century French novelist and playwright Honoré de Balzac.
  • 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: Marchais
Triple: [Georges Marchais, familyName, Marchais]
Generated description
Marchais is a French surname most notably borne by Georges Marchais, a prominent 20th-century French communist politician.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marchais
Target entity description: Marchais is a French surname most notably borne by Georges Marchais, a prominent 20th-century French communist politician.
  • A. Tourangeau
    Tourangeau is the French term for a person from the city of Tours in central France, particularly associated with the historic Touraine region.
  • B. Maurage
    Maurage is a village in the Walloon region of Belgium, forming part of the municipality of La Louvière in the province of Hainaut.
  • C. Kléber
    Kléber is a French tire brand known for producing mid-range, reliable tires for passenger cars and light commercial vehicles.
  • D. Martinet
    Martinet is a French surname most famously borne by Charles Martinet, the longtime voice actor of Nintendo’s Mario.
  • E. Honoré
    Honoré is the given name of the renowned 19th-century French novelist and playwright Honoré de Balzac.
  • 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_69ca8350897c819086cde7596fbe5fe7 completed March 30, 2026, 2:06 p.m.
NER Named-entity recognition batch_69cc486ece68819089c74bdf98b64490 completed March 31, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69ceccf559c4819089dfb8d6b11de1df completed April 2, 2026, 8:09 p.m.
NEDg Description generation batch_69cece8d530081908f5a52d5d76bd414 completed April 2, 2026, 8:16 p.m.
NED2 Entity disambiguation (via description) batch_69cecf7c66308190b9fb87bc0ab510a8 completed April 2, 2026, 8:20 p.m.
Created at: March 30, 2026, 6:30 p.m.