Triple

T262522
Position Surface form Disambiguated ID Type / Status
Subject Berlin E5567 entity
Predicate mergedWith P77 FINISHED
Object Cölln
Cölln was a historic town on the River Spree that, together with Berlin, formed the core of what later became the city of Berlin.
 E83946 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: Cölln | Statement: [Berlin, mergedWith, Cölln]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cölln
Context triple: [Berlin, mergedWith, Cölln]
  • A. Potsdam
    Potsdam is a historic German city near Berlin, known for its palaces, parks, and role in major 20th-century diplomatic events.
  • B. Spandau
    Spandau is a western borough of Berlin, Germany, known for its historic old town, fortress, and role as an important residential and industrial district.
  • C. Dresden
    Dresden is a historic cultural and economic center in eastern Germany, renowned for its baroque architecture, art collections, and reconstruction after World War II.
  • D. Leipzig
    Leipzig is a major city in eastern Germany known for its rich cultural heritage, vibrant music and arts scene, and important role in trade and commerce.
  • E. Bremen
    Bremen is a city-state in northwestern Germany comprising the cities of Bremen and Bremerhaven, known for its historic Hanseatic heritage and major port on the Weser River.
  • 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: Cölln
Triple: [Berlin, mergedWith, Cölln]
Generated description
Cölln was a historic town on the River Spree that, together with Berlin, formed the core of what later became the city of Berlin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cölln
Target entity description: Cölln was a historic town on the River Spree that, together with Berlin, formed the core of what later became the city of Berlin.
  • A. Potsdam
    Potsdam is a historic German city near Berlin, known for its palaces, parks, and role in major 20th-century diplomatic events.
  • B. Spandau
    Spandau is a western borough of Berlin, Germany, known for its historic old town, fortress, and role as an important residential and industrial district.
  • C. Dresden
    Dresden is a historic cultural and economic center in eastern Germany, renowned for its baroque architecture, art collections, and reconstruction after World War II.
  • D. Leipzig
    Leipzig is a major city in eastern Germany known for its rich cultural heritage, vibrant music and arts scene, and important role in trade and commerce.
  • E. Bremen
    Bremen is a city-state in northwestern Germany comprising the cities of Bremen and Bremerhaven, known for its historic Hanseatic heritage and major port on the Weser River.
  • 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_69a2580a64ac8190ad76e34bb0715b5e completed Feb. 28, 2026, 2:50 a.m.
NER Named-entity recognition batch_69a25d8c7f448190af9145256f994177 completed Feb. 28, 2026, 3:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69a5dc8df9708190976967ad4e45a597 completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5de11a0ac81909247a98bbc317cf7 completed March 2, 2026, 6:59 p.m.
NED2 Entity disambiguation (via description) batch_69a5febeeb908190a42d468edfe985ef completed March 2, 2026, 9:18 p.m.
Created at: Feb. 28, 2026, 2:55 a.m.