Triple

T10653301
Position Surface form Disambiguated ID Type / Status
Subject Denis Goldberg E251025 entity
Predicate spouse P13 FINISHED
Object Esme Bodenstein
Esme Bodenstein was the wife of South African anti-apartheid activist Denis Goldberg and a fellow supporter of the struggle against apartheid.
E889041 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: Esme Bodenstein | Statement: [Denis Goldberg, spouse, Esme Bodenstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Esme Bodenstein
Context triple: [Denis Goldberg, spouse, Esme Bodenstein]
  • A. Julia Mann
    Julia Mann was the mother of German novelist Thomas Mann and a key figure in the prominent Mann literary family.
  • B. Agathe Natanson
    Agathe Natanson is a French actress known for her work in film, television, and theater.
  • C. Eleanor Zellman
    Eleanor Zellman, better known by her stage name Eleanor Audley, was an American actress famed for her distinctive voice work in classic Disney films and for roles in mid-20th-century radio and television.
  • D. Rachel Buchman
    Rachel Buchman is the titular bride and central figure in the 2008 drama film "Rachel Getting Married," around whose wedding and family tensions the story revolves.
  • E. Emma Flegenheimer
    Emma Flegenheimer was the mother of notorious American mobster Dutch Schultz (born Arthur Flegenheimer).
  • 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: Esme Bodenstein
Triple: [Denis Goldberg, spouse, Esme Bodenstein]
Generated description
Esme Bodenstein was the wife of South African anti-apartheid activist Denis Goldberg and a fellow supporter of the struggle against apartheid.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Esme Bodenstein
Target entity description: Esme Bodenstein was the wife of South African anti-apartheid activist Denis Goldberg and a fellow supporter of the struggle against apartheid.
  • A. Julia Mann
    Julia Mann was the mother of German novelist Thomas Mann and a key figure in the prominent Mann literary family.
  • B. Agathe Natanson
    Agathe Natanson is a French actress known for her work in film, television, and theater.
  • C. Eleanor Zellman
    Eleanor Zellman, better known by her stage name Eleanor Audley, was an American actress famed for her distinctive voice work in classic Disney films and for roles in mid-20th-century radio and television.
  • D. Rachel Buchman
    Rachel Buchman is the titular bride and central figure in the 2008 drama film "Rachel Getting Married," around whose wedding and family tensions the story revolves.
  • E. Emma Flegenheimer
    Emma Flegenheimer was the mother of notorious American mobster Dutch Schultz (born Arthur Flegenheimer).
  • 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_69d6aa5a4c4881908f39be6efe5981e5 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6dff85674819099bf40c9f4fede15 completed April 8, 2026, 11:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69deb07626988190a46d8a54eda156f5 completed April 14, 2026, 9:24 p.m.
NEDg Description generation batch_69dec2534728819095b3693120772da9 completed April 14, 2026, 10:40 p.m.
NED2 Entity disambiguation (via description) batch_69dec79b1b548190a74312284f98551c completed April 14, 2026, 11:02 p.m.
Created at: April 8, 2026, 9:06 p.m.