Triple

T16708810
Position Surface form Disambiguated ID Type / Status
Subject Anne de Zogheb E406044 entity
Predicate mother P120 FINISHED
Object Mildred de Zogheb
Mildred de Zogheb was a member of the de Zogheb family, known as the mother of Anne de Zogheb, who became a prominent fashion model and the wife of singer Paul Anka.
 E1229720 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: Mildred de Zogheb | Statement: [Anne de Zogheb, mother, Mildred de Zogheb]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mildred de Zogheb
Context triple: [Anne de Zogheb, mother, Mildred de Zogheb]
  • A. Marie Saine-Firdaus
    Marie Saine-Firdaus is a Gambian lawyer and politician who served as the country's Attorney General and Minister of Justice.
  • B. Violette Aziz
    Violette Aziz is best known as the wife of former Iraqi Deputy Prime Minister and longtime Saddam Hussein confidant Tariq Aziz.
  • C. Mireille Mossé
    Mireille Mossé is an actress known for her role in the visually distinctive French fantasy film "The City of Lost Children."
  • D. Marcelle Hainia
    Marcelle Hainia was a French actress known for her role in the classic 1932 film "Boudu Saved from Drowning."
  • E. Sylvia Maklès
    Sylvia Maklès was a French actress and intellectual figure associated with the avant-garde literary milieu of the early 20th century.
  • 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: Mildred de Zogheb
Triple: [Anne de Zogheb, mother, Mildred de Zogheb]
Generated description
Mildred de Zogheb was a member of the de Zogheb family, known as the mother of Anne de Zogheb, who became a prominent fashion model and the wife of singer Paul Anka.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mildred de Zogheb
Target entity description: Mildred de Zogheb was a member of the de Zogheb family, known as the mother of Anne de Zogheb, who became a prominent fashion model and the wife of singer Paul Anka.
  • A. Marie Saine-Firdaus
    Marie Saine-Firdaus is a Gambian lawyer and politician who served as the country's Attorney General and Minister of Justice.
  • B. Violette Aziz
    Violette Aziz is best known as the wife of former Iraqi Deputy Prime Minister and longtime Saddam Hussein confidant Tariq Aziz.
  • C. Mireille Mossé
    Mireille Mossé is an actress known for her role in the visually distinctive French fantasy film "The City of Lost Children."
  • D. Marcelle Hainia
    Marcelle Hainia was a French actress known for her role in the classic 1932 film "Boudu Saved from Drowning."
  • E. Sylvia Maklès
    Sylvia Maklès was a French actress and intellectual figure associated with the avant-garde literary milieu of the early 20th century.
  • 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_69d8838db21081909589220fd71440a4 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e38650c3808190a561f22b169dc3ae completed April 18, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0091a739308190b4d645e096d1710b completed May 10, 2026, 2:09 p.m.
NEDg Description generation batch_6a00935ad86881908c45cdb513313a1d completed May 10, 2026, 2:16 p.m.
NED2 Entity disambiguation (via description) batch_6a009a0bd7f8819090fb16d88108b96d completed May 10, 2026, 2:45 p.m.
Created at: April 10, 2026, 5:20 a.m.