Triple

T17725676
Position Surface form Disambiguated ID Type / Status
Subject Don Zagier E442454 entity
Predicate doctoralAdvisor P167 FINISHED
Object Günter Harder
Günter Harder is a German mathematician known for his work in arithmetic geometry, automorphic forms, and the cohomology of arithmetic groups.
 E1552769 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: Günter Harder | Statement: [Don Zagier, doctoralAdvisor, Günter Harder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Günter Harder
Context triple: [Don Zagier, doctoralAdvisor, Günter Harder]
  • A. Wolfgang Neuss
    Wolfgang Neuss was a prominent German cabaret artist, comedian, and actor known for his sharp political satire and influential role in postwar German entertainment.
  • B. Gerhard Feige
    Gerhard Feige is a German Roman Catholic prelate and theologian who serves as the bishop of Magdeburg.
  • C. Günter Mittag
    Günter Mittag was a prominent East German politician and economist who played a key role in managing the GDR’s centrally planned economy and held several top leadership positions in the Socialist Unity Party.
  • D. Gerhard Bading
    Gerhard Bading was a Milwaukee politician who succeeded Emil Seidel as mayor in the early 20th century.
  • E. Gerhard H. Brandt
    Gerhard H. Brandt is a film producer best known for his work on the movie "Fedora."
  • 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: Günter Harder
Triple: [Don Zagier, doctoralAdvisor, Günter Harder]
Generated description
Günter Harder is a German mathematician known for his work in arithmetic geometry, automorphic forms, and the cohomology of arithmetic groups.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Günter Harder
Target entity description: Günter Harder is a German mathematician known for his work in arithmetic geometry, automorphic forms, and the cohomology of arithmetic groups.
  • A. Wolfgang Neuss
    Wolfgang Neuss was a prominent German cabaret artist, comedian, and actor known for his sharp political satire and influential role in postwar German entertainment.
  • B. Gerhard Feige
    Gerhard Feige is a German Roman Catholic prelate and theologian who serves as the bishop of Magdeburg.
  • C. Günter Mittag
    Günter Mittag was a prominent East German politician and economist who played a key role in managing the GDR’s centrally planned economy and held several top leadership positions in the Socialist Unity Party.
  • D. Gerhard Bading
    Gerhard Bading was a Milwaukee politician who succeeded Emil Seidel as mayor in the early 20th century.
  • E. Gerhard H. Brandt
    Gerhard H. Brandt is a film producer best known for his work on the movie "Fedora."
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47489c59c8190bbffefad20dc6346 completed April 19, 2026, 6:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b97fc2600819085486a9d540c9df3 completed May 18, 2026, 10:51 p.m.
NEDg Description generation batch_6a0b9884cb548190958d16f42be4bea8 completed May 18, 2026, 10:53 p.m.
NED2 Entity disambiguation (via description) batch_6a0b98e7887881909ec9cc4a2a2167c5 completed May 18, 2026, 10:55 p.m.
Created at: April 10, 2026, 10:07 a.m.