Triple

T3078034
Position Surface form Disambiguated ID Type / Status
Subject Laurent Fabius E64185 entity
Predicate mother P120 FINISHED
Object Louise Mortimer
Louise Mortimer was the mother of French Socialist politician and former Prime Minister Laurent Fabius.
E325765 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: Louise Mortimer | Statement: [Laurent Fabius, mother, Louise Mortimer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Louise Mortimer
Context triple: [Laurent Fabius, mother, Louise Mortimer]
  • A. Louise
    Louise is a feminine given name of French origin, traditionally associated with nobility and widely used in many European and English-speaking countries.
  • B. Louisa Hawkins
    Louisa Hawkins was the first wife of Sir Arthur Conan Doyle, the famed British author and creator of Sherlock Holmes.
  • C. Louise Carter
    Louise Carter was an American stage and film actress active in the early 20th century, known for her character roles in Hollywood productions.
  • D. Louisa Burton
    Louisa Burton was the wife of influential 19th-century English architect and designer Augustus Welby Northmore Pugin.
  • E. Sybylla Melvyn
    Sybylla Melvyn is an independent, imaginative young woman in rural Australia whose struggle against societal expectations and desire for artistic and personal freedom drive the narrative of *My Brilliant Career*.
  • 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: Louise Mortimer
Triple: [Laurent Fabius, mother, Louise Mortimer]
Generated description
Louise Mortimer was the mother of French Socialist politician and former Prime Minister Laurent Fabius.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Louise Mortimer
Target entity description: Louise Mortimer was the mother of French Socialist politician and former Prime Minister Laurent Fabius.
  • A. Louise
    Louise is a feminine given name of French origin, traditionally associated with nobility and widely used in many European and English-speaking countries.
  • B. Louisa Hawkins
    Louisa Hawkins was the first wife of Sir Arthur Conan Doyle, the famed British author and creator of Sherlock Holmes.
  • C. Louise Carter
    Louise Carter was an American stage and film actress active in the early 20th century, known for her character roles in Hollywood productions.
  • D. Louisa Burton
    Louisa Burton was the wife of influential 19th-century English architect and designer Augustus Welby Northmore Pugin.
  • E. Sybylla Melvyn
    Sybylla Melvyn is an independent, imaginative young woman in rural Australia whose struggle against societal expectations and desire for artistic and personal freedom drive the narrative of *My Brilliant Career*.
  • 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_69ad857a8aec8190bfdfd9c14554ac5a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1a6f6148190ae5cd6e45eda9006 completed March 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f88d32a08190b4e18da4b26b534c completed March 11, 2026, 11:19 p.m.
NEDg Description generation batch_69b1f8f83d10819099feb370fa9f14af completed March 11, 2026, 11:21 p.m.
NED2 Entity disambiguation (via description) batch_69b1fd02557c81908d42bb1a10024502 completed March 11, 2026, 11:38 p.m.
Created at: March 8, 2026, 3:02 p.m.