Triple

T10834684
Position Surface form Disambiguated ID Type / Status
Subject Diemel E255721 entity
Predicate hasTributary P415 FINISHED
Object Orpe
Orpe is a small river in Germany that serves as a tributary to the Diemel.
 E888730 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: Orpe | Statement: [Diemel, hasTributary, Orpe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orpe
Context triple: [Diemel, hasTributary, Orpe]
  • A. Peurion
    Peurion is a white grape variety historically cultivated in parts of Europe, known as a descendant of the ancient Heunisch Weiss lineage.
  • B. Oesilo
    Oesilo is an administrative post in the Oecusse exclave of East Timor, known for its rural communities and border location with Indonesian West Timor.
  • C. Orbiel
    The Orbiel is a river in southern France that flows through the Aude department before joining the Aude River.
  • D. Orsa
    Orsa is a small locality and municipality in central Sweden known for its forests, lakes, and traditional Dalarna culture.
  • E. Oros
    Oros is a surname most notably associated with Joe Oros, an American automobile designer known for his work at Ford.
  • 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: Orpe
Triple: [Diemel, hasTributary, Orpe]
Generated description
Orpe is a small river in Germany that serves as a tributary to the Diemel.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orpe
Target entity description: Orpe is a small river in Germany that serves as a tributary to the Diemel.
  • A. Peurion
    Peurion is a white grape variety historically cultivated in parts of Europe, known as a descendant of the ancient Heunisch Weiss lineage.
  • B. Oesilo
    Oesilo is an administrative post in the Oecusse exclave of East Timor, known for its rural communities and border location with Indonesian West Timor.
  • C. Orbiel
    The Orbiel is a river in southern France that flows through the Aude department before joining the Aude River.
  • D. Orsa
    Orsa is a small locality and municipality in central Sweden known for its forests, lakes, and traditional Dalarna culture.
  • E. Oros
    Oros is a surname most notably associated with Joe Oros, an American automobile designer known for his work at Ford.
  • 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_69d6aa81a5d08190aa86689061d1ddd2 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d74425447081908fb51c7edf54af67 completed April 9, 2026, 6:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69deb11a264c8190829ff89f0b13d063 completed April 14, 2026, 9:26 p.m.
NEDg Description generation batch_69deb4deef988190bfcf9a9529738899 completed April 14, 2026, 9:42 p.m.
NED2 Entity disambiguation (via description) batch_69deb54876ac81909222a7c25bccefe5 completed April 14, 2026, 9:44 p.m.
Created at: April 8, 2026, 9:19 p.m.