Triple

T13110613
Position Surface form Disambiguated ID Type / Status
Subject Hof (Saale) E310959 entity
Predicate hasSubdivision P747 FINISHED
Object Hof-Moschendorf
Hof-Moschendorf is a district of the Bavarian city of Hof in Germany, known primarily as a residential area within the urban region.
E1119373 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: Hof-Moschendorf | Statement: [Hof (Saale), hasSubdivision, Hof-Moschendorf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hof-Moschendorf
Context triple: [Hof (Saale), hasSubdivision, Hof-Moschendorf]
  • A. Sierksdorf
    Sierksdorf is a small coastal municipality in northern Germany, known for its Baltic Sea beaches and the Hansa-Park amusement park.
  • B. Schmargendorf
    Schmargendorf is a residential locality in southwestern Berlin known for its quiet streets, historic buildings, and proximity to the Grunewald forest.
  • C. Neuendorf
    Neuendorf is a small village on the Baltic Sea island of Hiddensee in Germany, known for its traditional thatched houses and maritime character.
  • D. Hennigsdorf
    Hennigsdorf is a town in the German state of Brandenburg, located just northwest of Berlin and known for its industrial heritage and proximity to the Havel River.
  • E. Hademstorf
    Hademstorf is a small municipality in Lower Saxony, Germany, situated in the Heidekreis district.
  • 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: Hof-Moschendorf
Triple: [Hof (Saale), hasSubdivision, Hof-Moschendorf]
Generated description
Hof-Moschendorf is a district of the Bavarian city of Hof in Germany, known primarily as a residential area within the urban region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hof-Moschendorf
Target entity description: Hof-Moschendorf is a district of the Bavarian city of Hof in Germany, known primarily as a residential area within the urban region.
  • A. Sierksdorf
    Sierksdorf is a small coastal municipality in northern Germany, known for its Baltic Sea beaches and the Hansa-Park amusement park.
  • B. Schmargendorf
    Schmargendorf is a residential locality in southwestern Berlin known for its quiet streets, historic buildings, and proximity to the Grunewald forest.
  • C. Neuendorf
    Neuendorf is a small village on the Baltic Sea island of Hiddensee in Germany, known for its traditional thatched houses and maritime character.
  • D. Hennigsdorf
    Hennigsdorf is a town in the German state of Brandenburg, located just northwest of Berlin and known for its industrial heritage and proximity to the Havel River.
  • E. Hademstorf
    Hademstorf is a small municipality in Lower Saxony, Germany, situated in the Heidekreis district.
  • 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_69d806a872d08190a329806f8ff30df4 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9817e4f408190b77c198b4157d77a completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0ccb9c3481908820f7620102e373 completed May 8, 2026, 4:18 p.m.
NEDg Description generation batch_69fe1903c0f88190b6f1a081047506d5 completed May 8, 2026, 5:10 p.m.
NED2 Entity disambiguation (via description) batch_69fe1980179481908b9f97e2f474e00d completed May 8, 2026, 5:12 p.m.
Created at: April 9, 2026, 9:05 p.m.