Triple

T20206355
Position Surface form Disambiguated ID Type / Status
Subject Bodenseekreis E493361 entity
Predicate hasTown P847 FINISHED
Object Markdorf
Markdorf is a small town in southern Germany near Lake Constance, known for its historic old town and scenic location in the Bodenseekreis district of Baden-Württemberg.
E1418298 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: Markdorf | Statement: [Bodenseekreis, hasTown, Markdorf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Markdorf
Context triple: [Bodenseekreis, hasTown, Markdorf]
  • A. Neudorf
    Neudorf is a residential district of Strasbourg, France, known for its dense urban fabric, local commerce, and proximity to the city center.
  • B. Neudorf
    Neudorf is a village-level subdivision of the Tyrolean municipality of Umhausen in western Austria.
  • C. Hitdorf
    Hitdorf is a district of the German city of Leverkusen, located along the Rhine and known for its riverside residential character.
  • D. Nyhausen
    Nyhausen is a locality in Germany historically noted as the birthplace of the Swedish nobleman and soldier Philip Christoph von Königsmarck.
  • E. Wendorf
    Wendorf is a small locality in northeastern Germany, known as the birthplace of the renowned German artist and sculptor Günther Uecker.
  • 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: Markdorf
Triple: [Bodenseekreis, hasTown, Markdorf]
Generated description
Markdorf is a small town in southern Germany near Lake Constance, known for its historic old town and scenic location in the Bodenseekreis district of Baden-Württemberg.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Markdorf
Target entity description: Markdorf is a small town in southern Germany near Lake Constance, known for its historic old town and scenic location in the Bodenseekreis district of Baden-Württemberg.
  • A. Neudorf
    Neudorf is a residential district of Strasbourg, France, known for its dense urban fabric, local commerce, and proximity to the city center.
  • B. Neudorf
    Neudorf is a village-level subdivision of the Tyrolean municipality of Umhausen in western Austria.
  • C. Hitdorf
    Hitdorf is a district of the German city of Leverkusen, located along the Rhine and known for its riverside residential character.
  • D. Nyhausen
    Nyhausen is a locality in Germany historically noted as the birthplace of the Swedish nobleman and soldier Philip Christoph von Königsmarck.
  • E. Wendorf
    Wendorf is a small locality in northeastern Germany, known as the birthplace of the renowned German artist and sculptor Günther Uecker.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d922ebc8190ae012da8ceba74dd completed April 20, 2026, 6:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843ecd72c8190a605ccb8af032795 completed May 16, 2026, 10:16 a.m.
NEDg Description generation batch_6a0845193350819088523da3087fe421 completed May 16, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_6a0845e241048190ba7fb657d4dca3d7 completed May 16, 2026, 10:24 a.m.
Created at: April 11, 2026, 11:38 p.m.