Triple

T15634701
Position Surface form Disambiguated ID Type / Status
Subject Agger E375909 entity
Predicate hasTributary P415 FINISHED
Object Sülz
Sülz is a river in North Rhine-Westphalia, Germany, that flows through the Bergisches Land region before joining the Agger.
 E1168070 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: Sülz | Statement: [Agger, hasTributary, Sülz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sülz
Context triple: [Agger, hasTributary, Sülz]
  • A. Vohenstrauß
    Vohenstrauß is a small town in the Upper Palatinate region of Bavaria, Germany, known for its historic architecture and surrounding forested landscapes.
  • B. Saaleck
    Saaleck is a small locality in Germany, historically notable as the birthplace of the pioneering Protestant theologian Johann Salomo Semler.
  • C. Vechigen
    Vechigen is a rural municipality in the canton of Bern, Switzerland, known for its scattered settlements and agricultural landscape near the city of Bern.
  • D. Voitsberg
    Voitsberg is a small town in southeastern Austria known for its industrial heritage and location within the federal state of Styria.
  • E. Santruschitz
    Santruschitz is the family name of Hermine "Miep" Santruschitz, better known as Miep Gies, one of the Dutch citizens who helped hide Anne Frank and her family during World War II.
  • 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: Sülz
Triple: [Agger, hasTributary, Sülz]
Generated description
Sülz is a river in North Rhine-Westphalia, Germany, that flows through the Bergisches Land region before joining the Agger.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sülz
Target entity description: Sülz is a river in North Rhine-Westphalia, Germany, that flows through the Bergisches Land region before joining the Agger.
  • A. Vohenstrauß
    Vohenstrauß is a small town in the Upper Palatinate region of Bavaria, Germany, known for its historic architecture and surrounding forested landscapes.
  • B. Saaleck
    Saaleck is a small locality in Germany, historically notable as the birthplace of the pioneering Protestant theologian Johann Salomo Semler.
  • C. Vechigen
    Vechigen is a rural municipality in the canton of Bern, Switzerland, known for its scattered settlements and agricultural landscape near the city of Bern.
  • D. Voitsberg
    Voitsberg is a small town in southeastern Austria known for its industrial heritage and location within the federal state of Styria.
  • E. Santruschitz
    Santruschitz is the family name of Hermine "Miep" Santruschitz, better known as Miep Gies, one of the Dutch citizens who helped hide Anne Frank and her family during World War II.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eb8b4c48190b80fea6877483089 completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f472b648190b7cd532a1b16373e completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff606f627081909e6ea230f30c917b completed May 9, 2026, 4:27 p.m.
NED2 Entity disambiguation (via description) batch_69ff6136a8c88190a83ad9232a338082 completed May 9, 2026, 4:30 p.m.
Created at: April 10, 2026, 4:14 a.m.