Triple
T9336866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Edwina Currie |
E224665
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object | Edwina |
E230615
|
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: Edwina | Statement: [Edwina Currie, givenName, Edwina]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edwina Context triple: [Edwina Currie, givenName, Edwina]
-
A.
Edwina
chosen
Edwina is a feminine given name of Old English origin, meaning "rich friend" or "prosperous friend."
-
B.
Edwina Ashley
Edwina Ashley was a British heiress, socialite, and humanitarian who became Countess Mountbatten of Burma through her marriage to Louis Mountbatten.
-
C.
Camilla Rutherford
Camilla Rutherford is a British actress and former model best known for her roles in period dramas such as "Gosford Park" and "Gosford Park."
-
D.
Edwina Brown
Edwina Brown is a fictional character known as one of the Brown sisters in Enid Bagnold’s novel "National Velvet," set in the English countryside.
-
E.
Edwina Booth
Edwina Booth was the daughter of famed 19th-century American actor Edwin Booth and later became known for preserving and promoting her father's theatrical legacy.
- 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_69ca84286fcc81909f6e7fd7a7e862a2 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd37f161e481908e23c1ec7e5fcf97 |
completed | April 1, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0f3b37b408190957c371233d8a3bd |
completed | April 4, 2026, 11:19 a.m. |
Created at: March 30, 2026, 7:40 p.m.