Triple

T2179925
Position Surface form Disambiguated ID Type / Status
Subject Martha E49016 entity
Predicate hasVariant P455 FINISHED
Object Marthe
Marthe is a feminine given name, commonly used in French and other European languages, that is a variant of the name Martha.
 E241286 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: Marthe | Statement: [Martha, hasVariant, Marthe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marthe
Context triple: [Martha, hasVariant, Marthe]
  • A. Marthe Keller
    Marthe Keller is a Swiss actress and former opera director known for her international film career, including prominent roles in 1970s Hollywood thrillers and European cinema.
  • B. Françoise
    Françoise is the given name of Louise de La Vallière, a 17th-century French noblewoman best known as a mistress of King Louis XIV.
  • C. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • D. Pierrette
    Pierrette is a French feminine given name, traditionally considered the female form of Pierre.
  • E. Antoinette de Mauban
    Antoinette de Mauban is a sophisticated and morally conflicted noblewoman in Anthony Hope’s adventure novel "The Prisoner of Zenda," whose shifting loyalties significantly influence the political intrigue of the story.
  • 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: Marthe
Triple: [Martha, hasVariant, Marthe]
Generated description
Marthe is a feminine given name, commonly used in French and other European languages, that is a variant of the name Martha.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marthe
Target entity description: Marthe is a feminine given name, commonly used in French and other European languages, that is a variant of the name Martha.
  • A. Marthe Keller
    Marthe Keller is a Swiss actress and former opera director known for her international film career, including prominent roles in 1970s Hollywood thrillers and European cinema.
  • B. Françoise
    Françoise is the given name of Louise de La Vallière, a 17th-century French noblewoman best known as a mistress of King Louis XIV.
  • C. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • D. Pierrette
    Pierrette is a French feminine given name, traditionally considered the female form of Pierre.
  • E. Antoinette de Mauban
    Antoinette de Mauban is a sophisticated and morally conflicted noblewoman in Anthony Hope’s adventure novel "The Prisoner of Zenda," whose shifting loyalties significantly influence the political intrigue of the story.
  • 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_69a88aa72d348190a9544bb5b8a4e71d completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abbef0e2f0819080ca457fe3b8b419 completed March 7, 2026, 6 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5da5930c819087e71a609f76e269 completed March 9, 2026, 5:41 a.m.
NEDg Description generation batch_69ae5e4a45a08190bd96af6cda06ab35 completed March 9, 2026, 5:44 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ec4a35c8190bffc7a183497e764 completed March 9, 2026, 5:46 a.m.
Created at: March 4, 2026, 7:45 p.m.