Triple

T1213186
Position Surface form Disambiguated ID Type / Status
Subject Oświęcim E26048 entity
Predicate twinTown P1072 FINISHED
Object Kerpen
Kerpen is a town in North Rhine-Westphalia, Germany, known as the birthplace of Formula 1 champion Michael Schumacher and for its proximity to Cologne.
E153193 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: Kerpen | Statement: [Oświęcim, twinTown, Kerpen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kerpen
Context triple: [Oświęcim, twinTown, Kerpen]
  • A. Bütgenbach
    Bütgenbach is a municipality in eastern Belgium’s German-speaking Community, known for its scenic lake, outdoor recreation, and proximity to the strategic Elsenborn Ridge.
  • B. Neuss
    Neuss is a city in western Germany, near Düsseldorf, known as an administrative and commercial center with historical roots dating back to Roman times.
  • C. Herkingen
    Herkingen is a small Dutch village on the island of Goeree-Overflakkee in South Holland, known for its marina and water sports on the Grevelingenmeer.
  • D. Boudry
    Boudry is a municipality in the canton of Neuchâtel in western Switzerland, known as a historic town near Lake Neuchâtel.
  • E. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • 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: Kerpen
Triple: [Oświęcim, twinTown, Kerpen]
Generated description
Kerpen is a town in North Rhine-Westphalia, Germany, known as the birthplace of Formula 1 champion Michael Schumacher and for its proximity to Cologne.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kerpen
Target entity description: Kerpen is a town in North Rhine-Westphalia, Germany, known as the birthplace of Formula 1 champion Michael Schumacher and for its proximity to Cologne.
  • A. Bütgenbach
    Bütgenbach is a municipality in eastern Belgium’s German-speaking Community, known for its scenic lake, outdoor recreation, and proximity to the strategic Elsenborn Ridge.
  • B. Neuss
    Neuss is a city in western Germany, near Düsseldorf, known as an administrative and commercial center with historical roots dating back to Roman times.
  • C. Herkingen
    Herkingen is a small Dutch village on the island of Goeree-Overflakkee in South Holland, known for its marina and water sports on the Grevelingenmeer.
  • D. Boudry
    Boudry is a municipality in the canton of Neuchâtel in western Switzerland, known as a historic town near Lake Neuchâtel.
  • E. Oudenarde
    Oudenarde (Oudenaarde) is a historic town in East Flanders, Belgium, known for its medieval architecture, tapestry production, and role in early modern European conflicts.
  • 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_69a4948331fc8190b531ac9bec71c491 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be024e448190ba263a0cc5cc9cd5 completed March 1, 2026, 10:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69acc6185df88190bc658c948b31e606 completed March 8, 2026, 12:43 a.m.
NEDg Description generation batch_69acc6ea01188190b16a3698aeea2169 completed March 8, 2026, 12:46 a.m.
NED2 Entity disambiguation (via description) batch_69acc759809c81908c1ce0523311a7c5 completed March 8, 2026, 12:48 a.m.
Created at: March 1, 2026, 7:46 p.m.