Triple

T11369277
Position Surface form Disambiguated ID Type / Status
Subject Saarbrücken E269297 entity
Predicate hasMayor P185 FINISHED
Object Uwe Conradt
Uwe Conradt is a German politician who serves as the lord mayor of the city of Saarbrücken.
E921775 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: Uwe Conradt | Statement: [Saarbrücken, hasMayor, Uwe Conradt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Uwe Conradt
Context triple: [Saarbrücken, hasMayor, Uwe Conradt]
  • A. Michael Lohmann
    Michael Lohmann is a cinematographer best known for his work on the television film "Psych: The Movie."
  • B. Burkhard Dallwitz
    Burkhard Dallwitz is an Australian-based composer best known for his award-winning film and television scores, including his work on "The Truman Show."
  • C. Joseph Krafft
    Joseph Krafft was a member of the Krafft family, known in connection with the Austrian painter Johann Peter Krafft.
  • D. Claus-Johannes Voss
    Claus-Johannes Voss was a German entrepreneur best known as one of the key figures behind the creation of the luxury writing instrument brand Montblanc.
  • E. Hugo Bergmann
    Hugo Bergmann was a prominent Czech-Jewish philosopher and Zionist intellectual who became a leading figure in the cultural and academic life of early 20th-century Jerusalem.
  • 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: Uwe Conradt
Triple: [Saarbrücken, hasMayor, Uwe Conradt]
Generated description
Uwe Conradt is a German politician who serves as the lord mayor of the city of Saarbrücken.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Uwe Conradt
Target entity description: Uwe Conradt is a German politician who serves as the lord mayor of the city of Saarbrücken.
  • A. Michael Lohmann
    Michael Lohmann is a cinematographer best known for his work on the television film "Psych: The Movie."
  • B. Burkhard Dallwitz
    Burkhard Dallwitz is an Australian-based composer best known for his award-winning film and television scores, including his work on "The Truman Show."
  • C. Joseph Krafft
    Joseph Krafft was a member of the Krafft family, known in connection with the Austrian painter Johann Peter Krafft.
  • D. Claus-Johannes Voss
    Claus-Johannes Voss was a German entrepreneur best known as one of the key figures behind the creation of the luxury writing instrument brand Montblanc.
  • E. Hugo Bergmann
    Hugo Bergmann was a prominent Czech-Jewish philosopher and Zionist intellectual who became a leading figure in the cultural and academic life of early 20th-century Jerusalem.
  • 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_69d6aacca1048190b39dbbc2174616fa completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d7ea89e1148190b0ca29db9d7e2cbd completed April 9, 2026, 6:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69e5567b67f88190b0412e30b346d36d completed April 19, 2026, 10:26 p.m.
NEDg Description generation batch_69e562c7de3c8190befb6d7131129a2c completed April 19, 2026, 11:18 p.m.
NED2 Entity disambiguation (via description) batch_69e56a776390819082d47ad00cf1862b completed April 19, 2026, 11:51 p.m.
Created at: April 8, 2026, 9:33 p.m.