Triple
T10193171
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Hilda’s College |
E238088
|
entity |
| Predicate | region |
P40
|
FINISHED |
| Object | Parkville |
E624383
|
NE FINISHED |
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: Parkville | Statement: [St Hilda’s College, region, Parkville]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Parkville Context triple: [St Hilda’s College, region, Parkville]
-
A.
Parkville
chosen
Parkville is the main inner-city campus precinct of the University of Melbourne in Melbourne, Australia, known for its historic architecture and proximity to the central business district.
-
B.
Parkville
Parkville is a diverse, historically industrial neighborhood in Hartford, Connecticut, known for its vibrant arts scene and multicultural community.
-
C.
Parkville
Parkville is a suburban community in Maryland, United States, located just northeast of Baltimore City.
-
D.
Springville
Springville is a city in central Utah known for its arts community and proximity to the Wasatch Mountains.
-
E.
Bella Vista
Bella Vista is a historic, culturally vibrant neighborhood in South Philadelphia known for its Italian Market and diverse dining scene.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84de1b208190bf17bb305b002605 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdedc675008190b8248325f5a208bf |
completed | April 2, 2026, 4:17 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d317ca2cf481909cf715ef9248be3c |
completed | April 6, 2026, 2:17 a.m. |
Created at: March 30, 2026, 9:13 p.m.