Triple
T4253791
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Derwent (Tasmania) |
E95921
|
entity |
| Predicate | passesSettlement |
P10456
|
FINISHED |
| Object | Bellerive |
E351788
|
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: Bellerive | Statement: [River Derwent (Tasmania), passesSettlement, Bellerive]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bellerive Context triple: [River Derwent (Tasmania), passesSettlement, Bellerive]
-
A.
Bellerive
Bellerive is a locality within the Swiss municipality of Collonge-Bellerive, situated on the shores of Lake Geneva near Geneva.
-
B.
Bellerive
chosen
Bellerive is a riverside suburb of Hobart, Tasmania, known for its scenic waterfront and the Bellerive Oval cricket ground.
-
C.
De Benneville
De Benneville "Bert" Bell was a prominent American football executive best known as the NFL commissioner who helped modernize and popularize the league in the mid-20th century.
-
D.
Wasque Point
Wasque Point is a scenic, windswept coastal area on the southeastern tip of Chappaquiddick Island known for its beaches, fishing, and erosion-shaped shoreline.
-
E.
Bressant
Bressant is a novel by American author Julian Hawthorne, known as one of his early works in 19th-century fiction.
- 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_69b3453f759881909b91f01a1e82c036 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b34ebe6fbc8190a89269b478b3f435 |
completed | March 12, 2026, 11:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5a887703c81909a40f23f83154b8c |
completed | March 14, 2026, 6:27 p.m. |
Created at: March 12, 2026, 11:06 p.m.