Triple

T21513331
Position Surface form Disambiguated ID Type / Status
Subject U8 E530781 entity
Predicate hasStation P35 FINISHED
Object Pankstraße
Pankstraße is an underground station on Berlin’s U-Bahn network located in the Gesundbrunnen area of the city.
 E1496482 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: Pankstraße | Statement: [U8, hasStation, Pankstraße]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pankstraße
Context triple: [U8, hasStation, Pankstraße]
  • A. Poccistraße
    Poccistraße is a street in Munich, Germany, located in the city’s central area and serving as the namesake for the nearby U-Bahn station.
  • B. Bleibtreustraße
    Bleibtreustraße is a well-known street in Berlin’s Charlottenburg district, noted for its mix of shops, cafés, and historic residential buildings.
  • C. Sambesistraße
    Sambesistraße is a street in Berlin’s Afrikanisches Viertel, a neighborhood known for roads named after African regions, rivers, and countries.
  • D. Bolkerstraße
    Bolkerstraße is a historic and lively street in Düsseldorf’s Altstadt, known for its dense concentration of bars, restaurants, and nightlife.
  • E. Papestraße
    Papestraße was the former name of the Berlin Südkreuz railway station, a major transport hub in southern Berlin.
  • 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: Pankstraße
Triple: [U8, hasStation, Pankstraße]
Generated description
Pankstraße is an underground station on Berlin’s U-Bahn network located in the Gesundbrunnen area of the city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pankstraße
Target entity description: Pankstraße is an underground station on Berlin’s U-Bahn network located in the Gesundbrunnen area of the city.
  • A. Poccistraße
    Poccistraße is a street in Munich, Germany, located in the city’s central area and serving as the namesake for the nearby U-Bahn station.
  • B. Bleibtreustraße
    Bleibtreustraße is a well-known street in Berlin’s Charlottenburg district, noted for its mix of shops, cafés, and historic residential buildings.
  • C. Sambesistraße
    Sambesistraße is a street in Berlin’s Afrikanisches Viertel, a neighborhood known for roads named after African regions, rivers, and countries.
  • D. Bolkerstraße
    Bolkerstraße is a historic and lively street in Düsseldorf’s Altstadt, known for its dense concentration of bars, restaurants, and nightlife.
  • E. Papestraße
    Papestraße was the former name of the Berlin Südkreuz railway station, a major transport hub in southern Berlin.
  • 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_69e0c45c81f08190a6b8bbb70a45aae7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea88e6fc8190a4b73b8d32dae5a8 completed April 23, 2026, 9:46 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0a1e04258c819098f7254a63a7c0c3 completed May 17, 2026, 7:59 p.m.
NEDg Description generation batch_6a0a1eac9b648190881c97d474762fc0 completed May 17, 2026, 8:01 p.m.
NED2 Entity disambiguation (via description) batch_6a0a1f3b77488190bfb73b9e83446bb3 completed May 17, 2026, 8:04 p.m.
Created at: April 16, 2026, 6:25 p.m.