Triple
T19477065
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of Worcester |
E487272
|
entity |
| Predicate | hasCampus |
P116
|
FINISHED |
| Object |
Severn Campus
Severn Campus is a University of Worcester site focused on health, science, and professional education facilities along the River Severn in Worcester, England.
|
E1378360
|
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: Severn Campus Context triple: [University of Worcester, hasCampus, Severn Campus]
-
A.
Surrey campus
Surrey campus is Simon Fraser University's modern urban campus located in Surrey, British Columbia, known for its innovative design and focus on applied sciences, business, and interactive arts.
-
B.
Talbot Campus
Talbot Campus is Bournemouth University's main campus, housing the majority of its academic faculties, student facilities, and media and technology centers in Poole, Dorset, England.
-
C.
Outram Campus
Outram Campus is a National University of Singapore campus located in Singapore’s Outram district, primarily hosting medical and health-related education and research facilities.
-
D.
Chesterfield campus
Chesterfield campus is a University of Derby site in Chesterfield that provides higher education facilities and courses serving students in the town and surrounding region.
-
E.
Birley Campus
Birley Campus is a major Manchester Metropolitan University site in Manchester, England, known for its focus on education, health, and community engagement.
- 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: Severn Campus Triple: [University of Worcester, hasCampus, Severn Campus]
Generated description
Severn Campus is a University of Worcester site focused on health, science, and professional education facilities along the River Severn in Worcester, England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Severn Campus Target entity description: Severn Campus is a University of Worcester site focused on health, science, and professional education facilities along the River Severn in Worcester, England.
-
A.
Surrey campus
Surrey campus is Simon Fraser University's modern urban campus located in Surrey, British Columbia, known for its innovative design and focus on applied sciences, business, and interactive arts.
-
B.
Talbot Campus
Talbot Campus is Bournemouth University's main campus, housing the majority of its academic faculties, student facilities, and media and technology centers in Poole, Dorset, England.
-
C.
Outram Campus
Outram Campus is a National University of Singapore campus located in Singapore’s Outram district, primarily hosting medical and health-related education and research facilities.
-
D.
Chesterfield campus
Chesterfield campus is a University of Derby site in Chesterfield that provides higher education facilities and courses serving students in the town and surrounding region.
-
E.
Birley Campus
Birley Campus is a major Manchester Metropolitan University site in Manchester, England, known for its focus on education, health, and community engagement.
- 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.