Triple

T1678616
Position Surface form Disambiguated ID Type / Status
Subject Hugh Grant E36287 entity
Predicate spouse P13 FINISHED
Object Anna Eberstein
Anna Eberstein is a Swedish television producer and retail executive best known as the wife of British actor Hugh Grant.
E250374 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: Anna Eberstein | Statement: [Hugh Grant, spouse, Anna Eberstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anna Eberstein
Context triple: [Hugh Grant, spouse, Anna Eberstein]
  • A. Marianne Ehrlich
    Marianne Ehrlich was the daughter of Nobel Prize–winning German physician and immunologist Paul Ehrlich.
  • B. Elsa Löwenthal
    Elsa Löwenthal, better known as Elsa Einstein, was the second wife and cousin of physicist Albert Einstein and often managed his personal and social affairs.
  • C. 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.
  • D. Anna Schwarz
    Anna Schwarz was the wife of Nobel Prize–winning German novelist and playwright Günter Grass.
  • E. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • 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: Anna Eberstein
Triple: [Hugh Grant, spouse, Anna Eberstein]
Generated description
Anna Eberstein is a Swedish television producer and retail executive best known as the wife of British actor Hugh Grant.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anna Eberstein
Target entity description: Anna Eberstein is a Swedish television producer and retail executive best known as the wife of British actor Hugh Grant.
  • A. Marianne Ehrlich
    Marianne Ehrlich was the daughter of Nobel Prize–winning German physician and immunologist Paul Ehrlich.
  • B. Elsa Löwenthal
    Elsa Löwenthal, better known as Elsa Einstein, was the second wife and cousin of physicist Albert Einstein and often managed his personal and social affairs.
  • C. 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.
  • D. Anna Schwarz
    Anna Schwarz was the wife of Nobel Prize–winning German novelist and playwright Günter Grass.
  • E. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • 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_69a886139ed081909af0940aa9313512 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa625f7e1081909c3c4fe76625783a completed March 6, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae719e35e48190b43b2b2d7f40195a completed March 9, 2026, 7:07 a.m.
NEDg Description generation batch_69ae73b5df288190af7d368b866d20a2 completed March 9, 2026, 7:16 a.m.
NED2 Entity disambiguation (via description) batch_69ae7472fe948190b8df210de1afb159 completed March 9, 2026, 7:19 a.m.
Created at: March 4, 2026, 7:29 p.m.