Triple

T2982978
Position Surface form Disambiguated ID Type / Status
Subject Ruhr E80553 entity
Predicate flowsThrough P225 FINISHED
Object Witten
Witten is a city in the Ruhr region of western Germany known for its industrial heritage and location along the Ruhr River.
 E317101 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: Witten | Statement: [Ruhr, flowsThrough, Witten]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Witten
Context triple: [Ruhr, flowsThrough, Witten]
  • A. Witten
    Witten is a surname most notably associated with Edward Witten, a leading theoretical physicist and key figure in string theory and mathematical physics.
  • B. Wess
    Wess is a given name, typically used as a shortened or variant form of Wesley.
  • C. Weinberg
    Weinberg is a surname most prominently associated with Steven Weinberg, the Nobel Prize–winning theoretical physicist known for his work on the unification of fundamental forces.
  • D. Wirth
    Wirth is a Swiss surname most notably associated with computer scientist Niklaus Wirth, the designer of several influential programming languages.
  • E. Nerekhta
    Nerekhta is a historic Russian town known for its well-preserved traditional architecture and cultural heritage within Kostroma Oblast.
  • 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: Witten
Triple: [Ruhr, flowsThrough, Witten]
Generated description
Witten is a city in the Ruhr region of western Germany known for its industrial heritage and location along the Ruhr River.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Witten
Target entity description: Witten is a city in the Ruhr region of western Germany known for its industrial heritage and location along the Ruhr River.
  • A. Witten
    Witten is a surname most notably associated with Edward Witten, a leading theoretical physicist and key figure in string theory and mathematical physics.
  • B. Wess
    Wess is a given name, typically used as a shortened or variant form of Wesley.
  • C. Weinberg
    Weinberg is a surname most prominently associated with Steven Weinberg, the Nobel Prize–winning theoretical physicist known for his work on the unification of fundamental forces.
  • D. Wirth
    Wirth is a Swiss surname most notably associated with computer scientist Niklaus Wirth, the designer of several influential programming languages.
  • E. Nerekhta
    Nerekhta is a historic Russian town known for its well-preserved traditional architecture and cultural heritage within Kostroma Oblast.
  • 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_69ad8b15f6ac8190be5fd16a33edcb4f completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99a1ed44819085ae6d39943db1d9 completed March 8, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69b108f5e5c88190b9dd0a67cb159854 completed March 11, 2026, 6:17 a.m.
NEDg Description generation batch_69b10b3967ac81908390d684f2fb23b2 completed March 11, 2026, 6:27 a.m.
NED2 Entity disambiguation (via description) batch_69b10f312ec88190b632639acbd024dc completed March 11, 2026, 6:44 a.m.
Created at: March 8, 2026, 2:58 p.m.