Triple
T28863327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Durham University Queen’s Campus |
E728923
|
entity |
| Predicate | hostedDepartment |
P95215
|
FINISHED |
| Object | School of Medicine, Pharmacy and Health |
—
|
NE NERFINISHED |
How this triple was built (2 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: School of Medicine, Pharmacy and Health | Statement: [Durham University Queen’s Campus, hostedDepartment, School of Medicine, Pharmacy and Health]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostedDepartment Context triple: [Durham University Queen’s Campus, hostedDepartment, School of Medicine, Pharmacy and Health]
-
A.
basedInDepartment
chosen
Indicates that an entity operates or has its primary affiliation within a specific department.
-
B.
departmentServed
Indicates that an entity provides service or support to a particular department.
-
C.
motherDepartment
Indicates that one department is the parent or higher-level organizational unit of another department.
-
D.
laterDepartment
Indicates that one department occurs or is considered after another in a defined ordering or sequence.
-
E.
propDepartment
Indicates that one entity functions as a department or organizational subdivision associated with another entity.
- F. None of above.
Provenance (3 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_69f031a01cbc8190ba87270bb6fe4639 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f67f7efc3c8190986d2d95b7a23729 |
completed | May 2, 2026, 10:49 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 28, 2026, 6:48 a.m.