Triple

T11862017
Position Surface form Disambiguated ID Type / Status
Subject Artur Schnabel E282181 entity
Predicate spouse P13 FINISHED
Object Therese Behr-Schnabel
Therese Behr-Schnabel was a distinguished German contralto and influential voice teacher active in the late 19th and early 20th centuries.
E963792 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: Therese Behr-Schnabel | Statement: [Artur Schnabel, spouse, Therese Behr-Schnabel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Therese Behr-Schnabel
Context triple: [Artur Schnabel, spouse, Therese Behr-Schnabel]
  • A. Therese Weiss
    Therese Weiss was the wife of the influential German classical scholar and archaeologist Christian Gottlob Heyne.
  • B. Gjertrud Schnackenberg
    Gjertrud Schnackenberg is an American poet acclaimed for her intellectually rich, formally intricate verse and contributions to contemporary literature.
  • C. Traute Becker
    Traute Becker was the wife of Armin, Prince of Lippe, and thus a member of the German princely House of Lippe.
  • D. Cornelia Seibeld
    Cornelia Seibeld is a German politician who serves as the President (speaker) of the Berlin state parliament, the Abgeordnetenhaus von Berlin.
  • E. Elisabeth Eberl
    Elisabeth Eberl is an Austrian javelin thrower who has competed internationally, including at major European and world athletics events.
  • 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: Therese Behr-Schnabel
Triple: [Artur Schnabel, spouse, Therese Behr-Schnabel]
Generated description
Therese Behr-Schnabel was a distinguished German contralto and influential voice teacher active in the late 19th and early 20th centuries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Therese Behr-Schnabel
Target entity description: Therese Behr-Schnabel was a distinguished German contralto and influential voice teacher active in the late 19th and early 20th centuries.
  • A. Therese Weiss
    Therese Weiss was the wife of the influential German classical scholar and archaeologist Christian Gottlob Heyne.
  • B. Gjertrud Schnackenberg
    Gjertrud Schnackenberg is an American poet acclaimed for her intellectually rich, formally intricate verse and contributions to contemporary literature.
  • C. Traute Becker
    Traute Becker was the wife of Armin, Prince of Lippe, and thus a member of the German princely House of Lippe.
  • D. Cornelia Seibeld
    Cornelia Seibeld is a German politician who serves as the President (speaker) of the Berlin state parliament, the Abgeordnetenhaus von Berlin.
  • E. Elisabeth Eberl
    Elisabeth Eberl is an Austrian javelin thrower who has competed internationally, including at major European and world athletics events.
  • 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_69d6ab2945d081908a5851c916cbcfb5 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a69b16bc8190999a0c1240f9ce6a completed April 10, 2026, 7:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69f5f6366adc8190b5c8163af684afde completed May 2, 2026, 1:03 p.m.
NEDg Description generation batch_69f5fed2d57881908103ce89a365cdd4 completed May 2, 2026, 1:40 p.m.
NED2 Entity disambiguation (via description) batch_69f600bcaf288190b6204f985d3be638 completed May 2, 2026, 1:48 p.m.
Created at: April 8, 2026, 9:43 p.m.