Triple

T7037481
Position Surface form Disambiguated ID Type / Status
Subject Znojmo E163418 entity
Predicate hasTwinTown P919 FINISHED
Object Hollabrunn
Hollabrunn is a town in Lower Austria known as a local administrative and educational center within the Vienna metropolitan region.
 E636502 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: Hollabrunn | Statement: [Znojmo, hasTwinTown, Hollabrunn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hollabrunn
Context triple: [Znojmo, hasTwinTown, Hollabrunn]
  • 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. Carlby
    Carlby is a small rural village and civil parish in the South Kesteven district of Lincolnshire, England.
  • C. Litovel Brewery
    Litovel Brewery is a Czech brewery renowned for its traditional lagers and other beers produced in the town of Litovel in the Olomouc Region.
  • D. Carvel
    Carvel is a fictional small American town that serves as the primary setting for the Andy Hardy film series.
  • E. Kringla Bakeri og Kafe
    Kringla Bakeri og Kafe is a Norwegian-themed bakery and café at EPCOT in Walt Disney World, known for serving traditional Scandinavian pastries and snacks.
  • 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: Hollabrunn
Triple: [Znojmo, hasTwinTown, Hollabrunn]
Generated description
Hollabrunn is a town in Lower Austria known as a local administrative and educational center within the Vienna metropolitan region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hollabrunn
Target entity description: Hollabrunn is a town in Lower Austria known as a local administrative and educational center within the Vienna metropolitan region.
  • 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. Carlby
    Carlby is a small rural village and civil parish in the South Kesteven district of Lincolnshire, England.
  • C. Litovel Brewery
    Litovel Brewery is a Czech brewery renowned for its traditional lagers and other beers produced in the town of Litovel in the Olomouc Region.
  • D. Carvel
    Carvel is a fictional small American town that serves as the primary setting for the Andy Hardy film series.
  • E. Kringla Bakeri og Kafe
    Kringla Bakeri og Kafe is a Norwegian-themed bakery and café at EPCOT in Walt Disney World, known for serving traditional Scandinavian pastries and snacks.
  • 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_69c6885e7c1c8190be32a8f79ab4e0cf completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e221a7988190b6b69782a275abb7 completed March 27, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69c775a6e1a08190af7d121cb854118e completed March 28, 2026, 6:31 a.m.
NEDg Description generation batch_69c777e962448190993a019cb76781f8 completed March 28, 2026, 6:40 a.m.
NED2 Entity disambiguation (via description) batch_69c778ff705c8190909c03551292c5e9 completed March 28, 2026, 6:45 a.m.
Created at: March 27, 2026, 2:36 p.m.