Triple
T15710316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cassian Elwes |
E380818
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Elwes |
E700661
|
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: Elwes | Statement: [Cassian Elwes, familyName, Elwes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elwes Context triple: [Cassian Elwes, familyName, Elwes]
-
A.
Elwes
chosen
Elwes is an English surname most notably associated with actor Cary Elwes, known for roles in films such as "The Princess Bride."
-
B.
Lewes Brooks
Lewes Brooks is a low-lying wetland and grazing marsh in Sussex, England, known for its rich biodiversity and importance as a habitat for wetland birds and other wildlife.
-
C.
Wolvercote
Wolvercote is a village and suburb on the northern edge of Oxford, England, known for its historic character and proximity to the River Thames and Port Meadow.
-
D.
Devonside
Devonside is a small settlement located within the council area of Clackmannanshire in central Scotland.
-
E.
Nutfield
Nutfield is a village and civil parish in Surrey, England, known for its rural character and proximity to the town of Redhill.
- 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f8d8b648190842c635f2ae7bfa4 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff757d74b481909c8332a09ae36b4f |
completed | May 9, 2026, 5:57 p.m. |
Created at: April 10, 2026, 4:45 a.m.