Triple

T12454106
Position Surface form Disambiguated ID Type / Status
Subject Frankfurt City Hall complex E297609 entity
Predicate hasPart P35 FINISHED
Object Lange Schirn
Lange Schirn is a historic arcade-like passageway in Frankfurt’s old town, known for its traditional market stalls and connection to the Römer city hall complex.
 E983700 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: Lange Schirn | Statement: [Frankfurt City Hall complex, hasPart, Lange Schirn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lange Schirn
Context triple: [Frankfurt City Hall complex, hasPart, Lange Schirn]
  • A. Schlenze
    Schlenze is a small river in central Germany, known as a tributary of the Saale flowing through the state of Saxony-Anhalt.
  • B. Hornschuch
    Hornschuch is a German surname most notably associated with Karl Georg Hornschuch, a 19th-century botanist and bryologist.
  • C. Längenfeld
    Längenfeld is a Tyrolean municipality in western Austria known for its alpine scenery and thermal spa resort Aqua Dome in the Ötztal valley.
  • D. Schwerteck
    Schwerteck is a mountain peak in the Glockner Group of the Austrian Alps.
  • E. Finklehoffe
    Finklehoffe is the surname of Fred F. Finklehoffe, an American screenwriter and film producer active in Hollywood’s mid-20th century studio era.
  • 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: Lange Schirn
Triple: [Frankfurt City Hall complex, hasPart, Lange Schirn]
Generated description
Lange Schirn is a historic arcade-like passageway in Frankfurt’s old town, known for its traditional market stalls and connection to the Römer city hall complex.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lange Schirn
Target entity description: Lange Schirn is a historic arcade-like passageway in Frankfurt’s old town, known for its traditional market stalls and connection to the Römer city hall complex.
  • A. Schlenze
    Schlenze is a small river in central Germany, known as a tributary of the Saale flowing through the state of Saxony-Anhalt.
  • B. Hornschuch
    Hornschuch is a German surname most notably associated with Karl Georg Hornschuch, a 19th-century botanist and bryologist.
  • C. Längenfeld
    Längenfeld is a Tyrolean municipality in western Austria known for its alpine scenery and thermal spa resort Aqua Dome in the Ötztal valley.
  • D. Schwerteck
    Schwerteck is a mountain peak in the Glockner Group of the Austrian Alps.
  • E. Finklehoffe
    Finklehoffe is the surname of Fred F. Finklehoffe, an American screenwriter and film producer active in Hollywood’s mid-20th century studio era.
  • 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_69d6ada166c48190b902972cd2408fa3 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94da0b5988190b9df26dd3bb87337 completed April 10, 2026, 7:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f190c788190adceaab8117d52a6 completed May 2, 2026, 6:14 p.m.
NEDg Description generation batch_69f6405f9f6481909bcc3b2e3deeae7e completed May 2, 2026, 6:20 p.m.
NED2 Entity disambiguation (via description) batch_69f64168d23881908daee7d7cba2160d completed May 2, 2026, 6:24 p.m.
Created at: April 8, 2026, 9:56 p.m.