Triple
T7617396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Mary’s campus |
E172395
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object |
Imperial College London medical campuses network
Imperial College London medical campuses network is the collective group of the university’s teaching hospitals and clinical sites that support its medical education, research, and healthcare delivery.
|
E652631
|
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: Imperial College London medical campuses network | Statement: [St Mary’s campus, partOf, Imperial College London medical campuses network]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Imperial College London medical campuses network Context triple: [St Mary’s campus, partOf, Imperial College London medical campuses network]
-
A.
Imperial College Academic Health Science Centre
Imperial College Academic Health Science Centre is a major London-based academic health science partnership that integrates world-class medical research, education, and clinical care across multiple hospitals and Imperial College London.
-
B.
Imperial College School of Medicine
Imperial College School of Medicine is a leading UK medical school within Imperial College London, renowned for its research-intensive education and clinical training across multiple London hospital campuses.
-
C.
University College London Hospitals biomedical research network
The University College London Hospitals biomedical research network is a major academic health science partnership that coordinates and supports cutting-edge clinical and translational research across UCL-affiliated hospitals and institutes in London.
-
D.
Imperial College Healthcare NHS Trust
Imperial College Healthcare NHS Trust is a major NHS trust in London that runs several leading teaching hospitals and provides a wide range of acute and specialist healthcare services in partnership with Imperial College London.
-
E.
UCL Faculty of Medical Sciences
UCL Faculty of Medical Sciences is a major academic division of University College London that focuses on medical education, biomedical research, and clinical training in partnership with leading hospitals and research institutes.
- 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: Imperial College London medical campuses network Triple: [St Mary’s campus, partOf, Imperial College London medical campuses network]
Generated description
Imperial College London medical campuses network is the collective group of the university’s teaching hospitals and clinical sites that support its medical education, research, and healthcare delivery.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Imperial College London medical campuses network Target entity description: Imperial College London medical campuses network is the collective group of the university’s teaching hospitals and clinical sites that support its medical education, research, and healthcare delivery.
-
A.
Imperial College Academic Health Science Centre
chosen
Imperial College Academic Health Science Centre is a major London-based academic health science partnership that integrates world-class medical research, education, and clinical care across multiple hospitals and Imperial College London.
-
B.
Imperial College School of Medicine
Imperial College School of Medicine is a leading UK medical school within Imperial College London, renowned for its research-intensive education and clinical training across multiple London hospital campuses.
-
C.
University College London Hospitals biomedical research network
The University College London Hospitals biomedical research network is a major academic health science partnership that coordinates and supports cutting-edge clinical and translational research across UCL-affiliated hospitals and institutes in London.
-
D.
Imperial College Healthcare NHS Trust
Imperial College Healthcare NHS Trust is a major NHS trust in London that runs several leading teaching hospitals and provides a wide range of acute and specialist healthcare services in partnership with Imperial College London.
-
E.
UCL Faculty of Medical Sciences
UCL Faculty of Medical Sciences is a major academic division of University College London that focuses on medical education, biomedical research, and clinical training in partnership with leading hospitals and research institutes.
- F. None of above.
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_69c699506b308190826894dab1d9ea86 |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6fa46d95081909c01d1432585ab2a |
completed | March 27, 2026, 9:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c868714d7c8190aae66a3dd4e6214b |
completed | March 28, 2026, 11:46 p.m. |
| NEDg | Description generation | batch_69c86a93e34c81908aaf0edb023ee78c |
completed | March 28, 2026, 11:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c86af8330c8190a43c599e82fe465a |
completed | March 28, 2026, 11:57 p.m. |
Created at: March 27, 2026, 3:55 p.m.