Triple
T22014570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fanny and Elvis |
E543673
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Gwyneth Powell |
—
|
NE NERFINISHED |
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: Gwyneth Powell | Statement: [Fanny and Elvis, castMember, Gwyneth Powell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gwyneth Powell Context triple: [Fanny and Elvis, castMember, Gwyneth Powell]
-
A.
Gwyneth Powell
chosen
Gwyneth Powell was an English actress best known for her role as headmistress Mrs. McClusky in the long-running BBC school drama "Grange Hill."
-
B.
Gwyneth Hughes
Gwyneth Hughes is a British screenwriter and television producer known for her work on acclaimed dramas such as "The Girl," "Five Days," and various literary adaptations.
-
C.
Gwyneth Rees
Gwyneth Rees is a British children's author best known for her humorous and imaginative novels that often blend everyday life with elements of fantasy.
-
D.
Gwyneth Williams
Gwyneth Williams is a British media executive best known for her role as Controller of BBC Radio 4 and BBC Radio 4 Extra.
-
E.
Gwyneth Bevan
Gwyneth Bevan is a notable individual associated with the surname Bevan, recognized as a distinguished bearer of that name.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e2db934819095556760c7d85e4d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127a6bf6081909865781ea7937a1b |
completed | April 28, 2026, 9:33 p.m. |
Created at: April 16, 2026, 8:22 p.m.