Triple

T2154236
Position Surface form Disambiguated ID Type / Status
Subject Olivia de Havilland E47849 entity
Predicate relative P37 FINISHED
Object Lilian Fontaine
Lilian Fontaine was a British-born actress and the mother of famed Hollywood stars Olivia de Havilland and Joan Fontaine.
E245107 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: Lilian Fontaine | Statement: [Olivia de Havilland, relative, Lilian Fontaine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lilian Fontaine
Context triple: [Olivia de Havilland, relative, Lilian Fontaine]
  • A. Camille Lefèvre
    Camille Lefèvre was a Swiss architect best known for co-designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • B. Evangeline Bellefontaine
    Evangeline Bellefontaine is a fictional protagonist, likely from a narrative centered on her personal journey, relationships, and transformative experiences.
  • C. Alix de Foresta
    Alix de Foresta is a French aristocrat best known as the wife of Louis Napoléon, Prince Napoléon, a claimant to the former imperial throne of France.
  • D. Charlotte Charpentier
    Charlotte Charpentier was the wife of renowned Scottish novelist and poet Sir Walter Scott.
  • E. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • 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: Lilian Fontaine
Triple: [Olivia de Havilland, relative, Lilian Fontaine]
Generated description
Lilian Fontaine was a British-born actress and the mother of famed Hollywood stars Olivia de Havilland and Joan Fontaine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lilian Fontaine
Target entity description: Lilian Fontaine was a British-born actress and the mother of famed Hollywood stars Olivia de Havilland and Joan Fontaine.
  • A. Camille Lefèvre
    Camille Lefèvre was a Swiss architect best known for co-designing the Palais des Nations, the former League of Nations headquarters in Geneva.
  • B. Evangeline Bellefontaine
    Evangeline Bellefontaine is a fictional protagonist, likely from a narrative centered on her personal journey, relationships, and transformative experiences.
  • C. Alix de Foresta
    Alix de Foresta is a French aristocrat best known as the wife of Louis Napoléon, Prince Napoléon, a claimant to the former imperial throne of France.
  • D. Charlotte Charpentier
    Charlotte Charpentier was the wife of renowned Scottish novelist and poet Sir Walter Scott.
  • E. Marguerite Gaudelet
    Marguerite Gaudelet was the wife of French civil engineer Gustave Eiffel, famed designer of the Eiffel Tower.
  • 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_69a88a1d1fd8819088b34990d69a712f completed March 4, 2026, 7:38 p.m.
NER Named-entity recognition batch_69abbe64fdf081909a5ea6818bddd18c completed March 7, 2026, 5:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae653677ec8190ab0b044e005a9947 completed March 9, 2026, 6:14 a.m.
NEDg Description generation batch_69ae6656f7788190818179d923b11bba completed March 9, 2026, 6:19 a.m.
NED2 Entity disambiguation (via description) batch_69ae66cc3ac0819096e3f246b10e7761 completed March 9, 2026, 6:21 a.m.
Created at: March 4, 2026, 7:44 p.m.