Triple

T1695026
Position Surface form Disambiguated ID Type / Status
Subject Krefeld E36636 entity
Predicate twinTown P1072 FINISHED
Object Leverkusen
Leverkusen is a city in western Germany, known for its chemical industry and as the home of the football club Bayer 04 Leverkusen.
E296756 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: Leverkusen | Statement: [Krefeld, twinTown, Leverkusen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leverkusen
Context triple: [Krefeld, twinTown, Leverkusen]
  • A. Munich
    Munich is the capital and largest city of the German state of Bavaria, renowned for its rich cultural scene, historic architecture, and the annual Oktoberfest beer festival.
  • B. Wolfsburg
    Wolfsburg is a German city best known as the headquarters and main production site of the Volkswagen automobile company.
  • C. Ingolstadt
    Ingolstadt is a historic city in southern Germany known for its medieval architecture, university tradition, and role as a major hub of the automotive industry.
  • D. Dortmund
    Dortmund is a major city in western Germany known for its rich football culture, industrial heritage, and home club Borussia Dortmund.
  • E. Cologne
    Cologne is a historic German city on the Rhine River, renowned for its Gothic cathedral, vibrant cultural scene, and status as a major economic and media hub.
  • 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: Leverkusen
Triple: [Krefeld, twinTown, Leverkusen]
Generated description
Leverkusen is a city in western Germany, known for its chemical industry and as the home of the football club Bayer 04 Leverkusen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Leverkusen
Target entity description: Leverkusen is a city in western Germany, known for its chemical industry and as the home of the football club Bayer 04 Leverkusen.
  • A. Munich
    Munich is the capital and largest city of the German state of Bavaria, renowned for its rich cultural scene, historic architecture, and the annual Oktoberfest beer festival.
  • B. Wolfsburg
    Wolfsburg is a German city best known as the headquarters and main production site of the Volkswagen automobile company.
  • C. Ingolstadt
    Ingolstadt is a historic city in southern Germany known for its medieval architecture, university tradition, and role as a major hub of the automotive industry.
  • D. Dortmund
    Dortmund is a major city in western Germany known for its rich football culture, industrial heritage, and home club Borussia Dortmund.
  • E. Cologne
    Cologne is a historic German city on the Rhine River, renowned for its Gothic cathedral, vibrant cultural scene, and status as a major economic and media hub.
  • 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_69a886163dec8190859c514232a37a05 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa62b3b8908190afc3f9e4a384684f completed March 6, 2026, 5:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc01252ec8190a14ff51151d8e69e completed March 10, 2026, 6:54 a.m.
NEDg Description generation batch_69afc0d32d5881908b80e0bfca5cd873 completed March 10, 2026, 6:57 a.m.
NED2 Entity disambiguation (via description) batch_69afc133f8088190bd505db0d0d1d6f7 completed March 10, 2026, 6:59 a.m.
Created at: March 4, 2026, 7:30 p.m.