Triple
T3484738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | University of South Australia |
E73579
|
entity |
| Predicate | campus |
P269
|
FINISHED |
| Object |
Magill
Magill is a suburban campus of the University of South Australia located in Adelaide, known for its focus on education, arts, and social sciences.
|
E360298
|
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: Magill | Statement: [University of South Australia, campus, Magill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Magill Context triple: [University of South Australia, campus, Magill]
-
A.
Magruder
Magruder is a surname most notably associated with Jeb Stuart Magruder, a key figure in the Watergate scandal during the Nixon administration.
-
B.
Vidal
Vidal is a river flowing through the Occitanie region in southern France.
-
C.
Hamill
Hamill is the surname of Mark Hamill, the American actor best known for portraying Luke Skywalker in the Star Wars film series.
-
D.
McClurg
McClurg is the namesake of the historic McClurg Building, a notable structure recognized for its architectural and cultural significance.
-
E.
John Gardner
John Gardner was an American novelist and literary critic best known for works like "Grendel" and "The Sunlight Dialogues," as well as for his influential writings on the craft and morality of fiction.
- 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: Magill Triple: [University of South Australia, campus, Magill]
Generated description
Magill is a suburban campus of the University of South Australia located in Adelaide, known for its focus on education, arts, and social sciences.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Magill Target entity description: Magill is a suburban campus of the University of South Australia located in Adelaide, known for its focus on education, arts, and social sciences.
-
A.
Magruder
Magruder is a surname most notably associated with Jeb Stuart Magruder, a key figure in the Watergate scandal during the Nixon administration.
-
B.
Vidal
Vidal is a river flowing through the Occitanie region in southern France.
-
C.
Hamill
Hamill is the surname of Mark Hamill, the American actor best known for portraying Luke Skywalker in the Star Wars film series.
-
D.
McClurg
McClurg is the namesake of the historic McClurg Building, a notable structure recognized for its architectural and cultural significance.
-
E.
John Gardner
John Gardner was an American novelist and literary critic best known for works like "Grendel" and "The Sunlight Dialogues," as well as for his influential writings on the craft and morality of fiction.
- 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_69ad85b3c9b08190857cae74c7f36da9 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb795db88190805b26d9774fdb73 |
completed | March 8, 2026, 6:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b36820c90c819091b68cff7a0a2cda |
completed | March 13, 2026, 1:28 a.m. |
| NEDg | Description generation | batch_69b3687bb5148190b73fd365383c4a89 |
completed | March 13, 2026, 1:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b368ea71d081908332595324d8f873 |
completed | March 13, 2026, 1:31 a.m. |
Created at: March 8, 2026, 3:17 p.m.