Triple

T2972866
Position Surface form Disambiguated ID Type / Status
Subject Karl Benz E80320 entity
Predicate child P120 FINISHED
Object Ellen Benz
Ellen Benz was a daughter of German engineer and automobile pioneer Karl Benz.
E351166 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: Ellen Benz | Statement: [Karl Benz, child, Ellen Benz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ellen Benz
Context triple: [Karl Benz, child, Ellen Benz]
  • A. Ellen Benrath
    Ellen Benrath is known primarily as the wife of German actor Martin Benrath.
  • B. Anne Schaefer
    Anne Schaefer was an American silent film actress active in the early 20th century, appearing in numerous productions during the 1910s and 1920s.
  • C. Martha Schmellinsky
    Martha Schmellinsky was the wife of East German leader Walter Ulbricht and thus part of the political elite of the German Democratic Republic.
  • D. Beverley Schäfer
    Beverley Schäfer is a South African politician who serves as the Deputy Speaker of the Western Cape Provincial Parliament.
  • E. Annette Ziegler
    Annette Ziegler is an American jurist who serves as the Chief Justice of the Wisconsin Supreme Court.
  • 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: Ellen Benz
Triple: [Karl Benz, child, Ellen Benz]
Generated description
Ellen Benz was a daughter of German engineer and automobile pioneer Karl Benz.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ellen Benz
Target entity description: Ellen Benz was a daughter of German engineer and automobile pioneer Karl Benz.
  • A. Ellen Benrath
    Ellen Benrath is known primarily as the wife of German actor Martin Benrath.
  • B. Anne Schaefer
    Anne Schaefer was an American silent film actress active in the early 20th century, appearing in numerous productions during the 1910s and 1920s.
  • C. Martha Schmellinsky
    Martha Schmellinsky was the wife of East German leader Walter Ulbricht and thus part of the political elite of the German Democratic Republic.
  • D. Beverley Schäfer
    Beverley Schäfer is a South African politician who serves as the Deputy Speaker of the Western Cape Provincial Parliament.
  • E. Annette Ziegler
    Annette Ziegler is an American jurist who serves as the Chief Justice of the Wisconsin Supreme Court.
  • 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_69ad8b14ffe881908ffed62f9595c867 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad998656948190ba79d7196d735f34 completed March 8, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b324da09888190b3ea7763d3a09d5d completed March 12, 2026, 8:40 p.m.
NEDg Description generation batch_69b326960de48190abe69b3c140f4a4a completed March 12, 2026, 8:48 p.m.
NED2 Entity disambiguation (via description) batch_69b327b13c9c8190b8c431ca2ae61ef9 completed March 12, 2026, 8:53 p.m.
Created at: March 8, 2026, 2:58 p.m.