Triple
T5084232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amber Valley Borough |
E114596
|
entity |
| Predicate | namedAfter |
P63
|
FINISHED |
| Object | River Amber |
E169365
|
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: River Amber | Statement: [Amber Valley Borough, namedAfter, River Amber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: River Amber Context triple: [Amber Valley Borough, namedAfter, River Amber]
-
A.
River Amber
chosen
The River Amber is a small river in Derbyshire, England, that flows through the Amber Valley before joining the River Derwent.
-
B.
River Bourne
River Bourne is a small river in Dorset, England, that flows through and gives its name to the coastal town of Bournemouth.
-
C.
River Bourne
River Bourne is a chalk stream in Wiltshire, England, that flows through the Bourne Valley before joining the River Avon near Salisbury.
-
D.
The Lady in White
The Lady in White is a 1988 supernatural mystery-horror film in which Lukas Haas stars as a young boy who witnesses a ghostly apparition and uncovers a long-buried murder.
-
E.
Backstairs Passage
Backstairs Passage is a narrow strait in South Australia that separates Kangaroo Island from the mainland.
- 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_69bd443e941881908eb4e8c685b6f656 |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd75192d188190a7631bce5faf7de3 |
completed | March 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69beb13a8be08190a0f1fc3aec224dde |
completed | March 21, 2026, 2:54 p.m. |
Created at: March 20, 2026, 1:40 p.m.