Triple

T9606984
Position Surface form Disambiguated ID Type / Status
Subject Steve Forbes E231995 entity
Predicate spouse P13 FINISHED
Object Sabina Beekman
Sabina Beekman is the wife of American publishing executive and former presidential candidate Steve Forbes.
E809935 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: Sabina Beekman | Statement: [Steve Forbes, spouse, Sabina Beekman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sabina Beekman
Context triple: [Steve Forbes, spouse, Sabina Beekman]
  • A. Wivina Demeester
    Wivina Demeester is a Belgian politician known for her long-standing role in Flemish and national politics, particularly in public finance and infrastructure.
  • B. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • C. Simone Buitendijk
    Simone Buitendijk is a Dutch academic leader and scholar in higher education policy who has served as vice-chancellor of the University of Leeds.
  • D. Lotte Verbeek
    Lotte Verbeek is a Dutch actress and model best known internationally for her roles in historical drama series such as The Borgias and Outlander.
  • E. Saskia de Jonge
    Saskia de Jonge is a Dutch former competitive swimmer who specialized in freestyle events and represented the Netherlands in international competitions, including the Olympic Games.
  • 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: Sabina Beekman
Triple: [Steve Forbes, spouse, Sabina Beekman]
Generated description
Sabina Beekman is the wife of American publishing executive and former presidential candidate Steve Forbes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sabina Beekman
Target entity description: Sabina Beekman is the wife of American publishing executive and former presidential candidate Steve Forbes.
  • A. Wivina Demeester
    Wivina Demeester is a Belgian politician known for her long-standing role in Flemish and national politics, particularly in public finance and infrastructure.
  • B. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • C. Simone Buitendijk
    Simone Buitendijk is a Dutch academic leader and scholar in higher education policy who has served as vice-chancellor of the University of Leeds.
  • D. Lotte Verbeek
    Lotte Verbeek is a Dutch actress and model best known internationally for her roles in historical drama series such as The Borgias and Outlander.
  • E. Saskia de Jonge
    Saskia de Jonge is a Dutch former competitive swimmer who specialized in freestyle events and represented the Netherlands in international competitions, including the Olympic Games.
  • 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_69ca8485a90c819094fe40b42fde9d70 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd9a62372881908bf21be91e7285fb completed April 1, 2026, 10:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69d17942504481908e7147a0f56bdf96 completed April 4, 2026, 8:49 p.m.
NEDg Description generation batch_69d17a27596081909c6a2ec486480ce1 completed April 4, 2026, 8:52 p.m.
NED2 Entity disambiguation (via description) batch_69d17af1d1b48190b6f8350edfa4f5ef completed April 4, 2026, 8:56 p.m.
Created at: March 30, 2026, 8:08 p.m.