Triple

T11731593
Position Surface form Disambiguated ID Type / Status
Subject Klaus Schulze E278908 entity
Predicate familyName P18 FINISHED
Object Schulze
Schulze is a common German surname borne by numerous notable individuals across fields such as music, politics, and academia.
E942163 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: Schulze | Statement: [Klaus Schulze, familyName, Schulze]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Schulze
Context triple: [Klaus Schulze, familyName, Schulze]
  • A. Sainte-Laguë method
    The Sainte-Laguë method is a highest-averages system of party-list proportional representation that allocates seats more evenly between large and small parties than the d’Hondt method.
  • B. Kemeny–Young method
    The Kemeny–Young method is a voting system that ranks candidates by finding the ordering that best reflects voters’ pairwise preferences, minimizing overall disagreement.
  • C. Borda count
    The Borda count is a ranked voting method in which voters order candidates and points are assigned based on position in each ranking, with the candidate having the highest total score winning.
  • D. Condorcet criterion
    The Condorcet criterion is a voting system standard requiring that if a candidate would win every head-to-head contest against each other candidate, that candidate must be the overall election winner.
  • E. d’Hondt method
    The d’Hondt method is a highest-averages formula used in proportional representation systems to allocate seats or posts among parties based on their share of the vote.
  • 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: Schulze
Triple: [Klaus Schulze, familyName, Schulze]
Generated description
Schulze is a common German surname borne by numerous notable individuals across fields such as music, politics, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Schulze
Target entity description: Schulze is a common German surname borne by numerous notable individuals across fields such as music, politics, and academia.
  • A. Sainte-Laguë method
    The Sainte-Laguë method is a highest-averages system of party-list proportional representation that allocates seats more evenly between large and small parties than the d’Hondt method.
  • B. Kemeny–Young method
    The Kemeny–Young method is a voting system that ranks candidates by finding the ordering that best reflects voters’ pairwise preferences, minimizing overall disagreement.
  • C. Borda count
    The Borda count is a ranked voting method in which voters order candidates and points are assigned based on position in each ranking, with the candidate having the highest total score winning.
  • D. Condorcet criterion
    The Condorcet criterion is a voting system standard requiring that if a candidate would win every head-to-head contest against each other candidate, that candidate must be the overall election winner.
  • E. d’Hondt method
    The d’Hondt method is a highest-averages formula used in proportional representation systems to allocate seats or posts among parties based on their share of the vote.
  • 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_69d6aaffec6881908bead509e8621742 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4d94de08190a7184cf26d8cb94e completed April 10, 2026, 7:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef83f98fc481908015df3c4e5d7ed3 completed April 27, 2026, 3:42 p.m.
NEDg Description generation batch_69ef9b68309081909f3f614efeeb2ab1 completed April 27, 2026, 5:22 p.m.
NED2 Entity disambiguation (via description) batch_69efd6aba82c81909ff22e6b26db3cfe completed April 27, 2026, 9:35 p.m.
Created at: April 8, 2026, 9:41 p.m.