Triple

T1663075
Position Surface form Disambiguated ID Type / Status
Subject Cologne E35950 entity
Predicate hasLocalDialect P1762 FINISHED
Object Kölsch
Kölsch is a Ripuarian dialect of the German language traditionally spoken in and around the city of Cologne.
E187426 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: Kölsch | Statement: [Cologne, hasLocalDialect, Kölsch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kölsch
Context triple: [Cologne, hasLocalDialect, Kölsch]
  • A. Grimbergen
    Grimbergen is a municipality in the Flemish Brabant province of Belgium, known for its historic Norbertine abbey and the Grimbergen abbey beer.
  • B. Heineken lager beer
    Heineken lager beer is a globally recognized pale lager known for its distinctive green bottle, red star logo, and crisp, mildly bitter taste.
  • C. Amstel
    The Amstel is a river in the Netherlands that flows through Amsterdam and has given its name to the city and a well-known Dutch beer brand.
  • D. Amsterdam Amstel
    Amsterdam Amstel is a major railway and metro station in Amsterdam that serves as an important transport hub connecting regional and local lines.
  • E. Grolsch
    Grolsch is a Dutch brewery best known for its distinctive swing-top bottled beers and long-standing presence in the international beer market.
  • 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: Kölsch
Triple: [Cologne, hasLocalDialect, Kölsch]
Generated description
Kölsch is a Ripuarian dialect of the German language traditionally spoken in and around the city of Cologne.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kölsch
Target entity description: Kölsch is a Ripuarian dialect of the German language traditionally spoken in and around the city of Cologne.
  • A. Grimbergen
    Grimbergen is a municipality in the Flemish Brabant province of Belgium, known for its historic Norbertine abbey and the Grimbergen abbey beer.
  • B. Heineken lager beer
    Heineken lager beer is a globally recognized pale lager known for its distinctive green bottle, red star logo, and crisp, mildly bitter taste.
  • C. Amstel
    The Amstel is a river in the Netherlands that flows through Amsterdam and has given its name to the city and a well-known Dutch beer brand.
  • D. Amsterdam Amstel
    Amsterdam Amstel is a major railway and metro station in Amsterdam that serves as an important transport hub connecting regional and local lines.
  • E. Grolsch
    Grolsch is a Dutch brewery best known for its distinctive swing-top bottled beers and long-standing presence in the international beer market.
  • 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_69a88606aa808190aa0b421b4271f220 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90ab5d1a08190a3325ff203b573fb completed March 5, 2026, 4:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad682d968081909494920f3a7ea3af completed March 8, 2026, 12:14 p.m.
NEDg Description generation batch_69ad69017e448190b337337431c6f797 completed March 8, 2026, 12:18 p.m.
NED2 Entity disambiguation (via description) batch_69ad6966c3108190bf2519f698dd3903 completed March 8, 2026, 12:19 p.m.
Created at: March 4, 2026, 7:29 p.m.