Triple

T19477064
Position Surface form Disambiguated ID Type / Status
Subject University of Worcester E487272 entity
Predicate hasCampus P116 FINISHED
Object City Campus
City Campus is a University of Worcester site located in the city centre, housing modern teaching, learning, and professional facilities.
 E1378359 NE FINISHED

How this triple was built (3 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.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: City Campus
Context triple: [University of Worcester, hasCampus, City Campus]
  • A. City Campus
    City Campus is the main urban campus of the University of Dundee, housing most of its academic buildings and student facilities in the heart of Dundee, Scotland.
  • B. City Campus
    City Campus is the central urban campus of the University of Auckland, housing many of its core faculties, teaching facilities, and student services in downtown Auckland.
  • C. City Campus
    City Campus is one of the main University of Copenhagen sites, housing several of its faculties and academic departments in a central urban setting.
  • D. City Campus
    City Campus is the main urban campus of the University of Portsmouth, housing many of its academic buildings and student facilities in the heart of Portsmouth, England.
  • E. City Campus
    City Campus is Nottingham Trent University's main urban campus, located in the heart of Nottingham and housing many of its central academic and administrative facilities.
  • 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: City Campus
Triple: [University of Worcester, hasCampus, City Campus]
Generated description
City Campus is a University of Worcester site located in the city centre, housing modern teaching, learning, and professional facilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: City Campus
Target entity description: City Campus is a University of Worcester site located in the city centre, housing modern teaching, learning, and professional facilities.
  • A. City Campus
    City Campus is an urban teaching and learning site of the University of the West of England, Bristol, housing a range of academic facilities and student services in a city-centre setting.
  • B. City Campus
    City Campus is one of Leeds Beckett University's main urban campuses, located in central Leeds and housing a range of academic, administrative, and student facilities.
  • C. City Campus
    City Campus is the main urban campus of the University of Bradford, housing most of its academic, administrative, and student facilities in the city center.
  • D. City Campus
    City Campus is the main urban campus of the University of Portsmouth, housing many of its academic buildings and student facilities in the heart of Portsmouth, England.
  • E. City Campus
    City Campus is the main urban campus of the University of Dundee, housing most of its academic buildings and student facilities in the heart of Dundee, Scotland.
  • F. None of above. chosen

Provenance (4 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_69d8e8d924388190b847cb15bb3d0aff completed April 10, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_6a074053f7b48190a726ef5e285ed62a completed May 15, 2026, 3:48 p.m.
NEDg Description generation batch_6a07412a04d0819087c4dc7b5f2742ad completed May 15, 2026, 3:52 p.m.
NED2 Entity disambiguation (via description) batch_6a074197aa14819096a74aab7bca9e3c completed May 15, 2026, 3:53 p.m.
Created at: April 10, 2026, 1:39 p.m.