Triple

T16072742
Position Surface form Disambiguated ID Type / Status
Subject Marcus Goldman E389902 entity
Predicate spouse P13 FINISHED
Object Bertha Goldman
Bertha Goldman was the wife of Marcus Goldman, the founder of the financial firm that became Goldman Sachs.
E1192463 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: Bertha Goldman | Statement: [Marcus Goldman, spouse, Bertha Goldman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bertha Goldman
Context triple: [Marcus Goldman, spouse, Bertha Goldman]
  • A. Helene Shapiro
    Helene Shapiro is an American mathematician known for her work in linear algebra and matrix theory, and as a student of Olga Taussky-Todd.
  • B. Edna Fischel
    Edna Fischel was an American suffragist and civic leader known for her prominent role in the women’s voting rights movement in the early 20th century.
  • C. Ruth Schiff
    Ruth Schiff is a notable individual who shares the surname Schiff, recognized enough to be specifically cited as a bearer of the name.
  • D. Irene Lewisohn
    Irene Lewisohn was an American arts patron and educator who played a key role in developing early 20th-century theater and dance training in New York City.
  • E. Edith Weiss
    Edith Weiss is a notable individual recognized for bearing the surname Weiss, though specific widely known biographical or professional details about her are not well documented.
  • 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: Bertha Goldman
Triple: [Marcus Goldman, spouse, Bertha Goldman]
Generated description
Bertha Goldman was the wife of Marcus Goldman, the founder of the financial firm that became Goldman Sachs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bertha Goldman
Target entity description: Bertha Goldman was the wife of Marcus Goldman, the founder of the financial firm that became Goldman Sachs.
  • A. Helene Shapiro
    Helene Shapiro is an American mathematician known for her work in linear algebra and matrix theory, and as a student of Olga Taussky-Todd.
  • B. Edna Fischel
    Edna Fischel was an American suffragist and civic leader known for her prominent role in the women’s voting rights movement in the early 20th century.
  • C. Ruth Schiff
    Ruth Schiff is a notable individual who shares the surname Schiff, recognized enough to be specifically cited as a bearer of the name.
  • D. Irene Lewisohn
    Irene Lewisohn was an American arts patron and educator who played a key role in developing early 20th-century theater and dance training in New York City.
  • E. Edith Weiss
    Edith Weiss is a notable individual recognized for bearing the surname Weiss, though specific widely known biographical or professional details about her are not well documented.
  • 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_69d86daf32ec8190a8c0466c8f49c3c0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183bf6c488190b0099a00f13f2a69 completed April 17, 2026, 12:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffe484cef08190a3797c91a7025081 completed May 10, 2026, 1:51 a.m.
NEDg Description generation batch_69ffe67043588190864864d40956682b completed May 10, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_69ffe6f510cc8190b6b8c46c0356d36a completed May 10, 2026, 2:01 a.m.
Created at: April 10, 2026, 4:57 a.m.