Triple

T3197155
Position Surface form Disambiguated ID Type / Status
Subject Saboteur E66960 entity
Predicate castMember P1668 FINISHED
Object Alma Kruger
Alma Kruger was an American stage and film actress best known for her character roles in Hollywood movies of the 1930s and 1940s.
 E363191 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: Alma Kruger | Statement: [Saboteur, castMember, Alma Kruger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Alma Kruger
Context triple: [Saboteur, castMember, Alma Kruger]
  • A. Alma Wassermann
    Alma Wassermann was the wife of Nobel Prize–winning Yiddish author Isaac Bashevis Singer and a significant partner in his personal and literary life.
  • B. Helene Weber
    Helene Weber was a German politician and one of the few women involved in drafting both the Weimar and post–World War II German constitutions.
  • C. Edith Holländer
    Edith Holländer, later known as Edith Frank, was the mother of diarist Anne Frank and a German-born Jewish woman who perished in the Holocaust.
  • D. Luisa Haag
    Luisa Haag was the mother of the 19th-century Russian writer and political thinker Alexander Herzen.
  • E. Alma Muller
    Alma Muller was the wife of American character actor Frank Morgan, best known for his role as the Wizard in the 1939 film "The Wizard of Oz."
  • 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: Alma Kruger
Triple: [Saboteur, castMember, Alma Kruger]
Generated description
Alma Kruger was an American stage and film actress best known for her character roles in Hollywood movies of the 1930s and 1940s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Alma Kruger
Target entity description: Alma Kruger was an American stage and film actress best known for her character roles in Hollywood movies of the 1930s and 1940s.
  • A. Alma Wassermann
    Alma Wassermann was the wife of Nobel Prize–winning Yiddish author Isaac Bashevis Singer and a significant partner in his personal and literary life.
  • B. Helene Weber
    Helene Weber was a German politician and one of the few women involved in drafting both the Weimar and post–World War II German constitutions.
  • C. Edith Holländer
    Edith Holländer, later known as Edith Frank, was the mother of diarist Anne Frank and a German-born Jewish woman who perished in the Holocaust.
  • D. Luisa Haag
    Luisa Haag was the mother of the 19th-century Russian writer and political thinker Alexander Herzen.
  • E. Alma Muller
    Alma Muller was the wife of American character actor Frank Morgan, best known for his role as the Wizard in the 1939 film "The Wizard of Oz."
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7192994819084817307065a25e2 completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3738cbc1c819099a4f3e807c0eacf completed March 13, 2026, 2:16 a.m.
NEDg Description generation batch_69b374e50a088190ad4dc101efd68d54 completed March 13, 2026, 2:22 a.m.
NED2 Entity disambiguation (via description) batch_69b37544b04c819090e6f59babd8017e completed March 13, 2026, 2:24 a.m.
Created at: March 8, 2026, 3:07 p.m.