Triple

T19250290
Position Surface form Disambiguated ID Type / Status
Subject Maurice Ostrer E481369 entity
Predicate sibling P363 FINISHED
Object Mark Ostrer
Mark Ostrer was a member of the Ostrer family associated with the British film industry, related to prominent film executive Maurice Ostrer.
E481369 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: Mark Ostrer | Statement: [Maurice Ostrer, sibling, Mark Ostrer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Ostrer
Context triple: [Maurice Ostrer, sibling, Mark Ostrer]
  • A. Maurice Ostrer
    Maurice Ostrer was a British film executive best known for leading and shaping the output of the prominent mid-20th-century studio Gainsborough Pictures.
  • B. Albert Wolsky
    Albert Wolsky is an acclaimed American costume designer known for his work on numerous prominent films and stage productions, earning multiple Academy Awards and industry honors.
  • C. Joseph Wertheim
    Joseph Wertheim is one of the children of American investment banker and philanthropist Maurice Wertheim.
  • D. Henry Wertheim
    Henry Wertheim is a member of the Wertheim family, known primarily in relation to his brother, the American investment banker and philanthropist Maurice Wertheim.
  • E. James Lindenbaum
    James Lindenbaum is a technology entrepreneur best known as a co-founder of the cloud platform-as-a-service company Heroku.
  • 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: Mark Ostrer
Triple: [Maurice Ostrer, sibling, Mark Ostrer]
Generated description
Mark Ostrer was a member of the Ostrer family associated with the British film industry, related to prominent film executive Maurice Ostrer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mark Ostrer
Target entity description: Mark Ostrer was a member of the Ostrer family associated with the British film industry, related to prominent film executive Maurice Ostrer.
  • A. Maurice Ostrer chosen
    Maurice Ostrer was a British film executive best known for leading and shaping the output of the prominent mid-20th-century studio Gainsborough Pictures.
  • B. Albert Wolsky
    Albert Wolsky is an acclaimed American costume designer known for his work on numerous prominent films and stage productions, earning multiple Academy Awards and industry honors.
  • C. Joseph Wertheim
    Joseph Wertheim is one of the children of American investment banker and philanthropist Maurice Wertheim.
  • D. Henry Wertheim
    Henry Wertheim is a member of the Wertheim family, known primarily in relation to his brother, the American investment banker and philanthropist Maurice Wertheim.
  • E. James Lindenbaum
    James Lindenbaum is a technology entrepreneur best known as a co-founder of the cloud platform-as-a-service company Heroku.
  • F. None of above.

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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5fb3001308190913e24343769be8d completed April 20, 2026, 10:08 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0705e2d3948190b1ff731f648f68c7 completed May 15, 2026, 11:39 a.m.
NEDg Description generation batch_6a0706bd92b48190848fcf5be679d207 completed May 15, 2026, 11:42 a.m.
NED2 Entity disambiguation (via description) batch_6a070763ca5c81908afa73b30645223a completed May 15, 2026, 11:45 a.m.
Created at: April 10, 2026, 1:27 p.m.