Triple

T2729556
Position Surface form Disambiguated ID Type / Status
Subject Anatole Litvak E60276 entity
Predicate spouse P13 FINISHED
Object Sophie Steur
Sophie Steur was the wife of Ukrainian-born French-American film director Anatole Litvak, known for his work in Hollywood and European cinema.
E293239 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: Sophie Steur | Statement: [Anatole Litvak, spouse, Sophie Steur]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sophie Steur
Context triple: [Anatole Litvak, spouse, Sophie Steur]
  • A. Maayke Velders
    Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
  • B. 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.
  • C. Iris Steensma
    Iris Steensma is the troubled teenage prostitute character from Martin Scorsese’s 1976 film "Taxi Driver," whose role became iconic through Jodie Foster’s acclaimed performance.
  • D. Bianca Hoogendijk
    Bianca Hoogendijk is a Dutch woman best known as the wife of former Prime Minister of the Netherlands Jan Peter Balkenende.
  • E. Annik Penders
    Annik Penders is a Belgian communications professional best known as the wife of Belgian Prime Minister Alexander De Croo.
  • 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: Sophie Steur
Triple: [Anatole Litvak, spouse, Sophie Steur]
Generated description
Sophie Steur was the wife of Ukrainian-born French-American film director Anatole Litvak, known for his work in Hollywood and European cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sophie Steur
Target entity description: Sophie Steur was the wife of Ukrainian-born French-American film director Anatole Litvak, known for his work in Hollywood and European cinema.
  • A. Maayke Velders
    Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
  • B. 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.
  • C. Iris Steensma
    Iris Steensma is the troubled teenage prostitute character from Martin Scorsese’s 1976 film "Taxi Driver," whose role became iconic through Jodie Foster’s acclaimed performance.
  • D. Bianca Hoogendijk
    Bianca Hoogendijk is a Dutch woman best known as the wife of former Prime Minister of the Netherlands Jan Peter Balkenende.
  • E. Annik Penders
    Annik Penders is a Belgian communications professional best known as the wife of Belgian Prime Minister Alexander De Croo.
  • 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_69ab4b75cd908190b691ef0d1801acda completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdaeca6208190a586afb00747146a completed March 7, 2026, 7:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69afb69c9f648190bbbcfa42ab68c6f2 completed March 10, 2026, 6:13 a.m.
NEDg Description generation batch_69afb75ea498819089c79e63052e9696 completed March 10, 2026, 6:17 a.m.
NED2 Entity disambiguation (via description) batch_69afb83ba6dc8190931d691d3e354bd7 completed March 10, 2026, 6:20 a.m.
Created at: March 6, 2026, 9:56 p.m.