Triple
T22021873
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The White Queen |
E543864
|
entity |
| Predicate | composer |
P1361
|
FINISHED |
| Object | John Lunn |
—
|
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: John Lunn | Statement: [The White Queen, composer, John Lunn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Lunn Context triple: [The White Queen, composer, John Lunn]
-
A.
John Lunn
chosen
John Lunn is a Scottish composer best known for his award-winning musical scores for the television series Downton Abbey.
-
B.
Storm Thorgerson
Storm Thorgerson was a renowned British graphic designer best known for creating many iconic rock album covers, particularly for bands like Pink Floyd.
-
C.
Roy Lunn
Roy Lunn is a character portrayed by actor JJ Feild, likely within a film or television production.
-
D.
Kevin Godley
Kevin Godley is a British musician and acclaimed music video director, best known as a founding member of 10cc and for his innovative, visually inventive work in the medium.
-
E.
Anthony Buckley
Anthony Buckley is an Australian film producer and editor known for his work on notable Australian cinema, including influential dramas and documentaries.
- 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_69e11e2e8ea4819084210fe06d3a1b8d |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127c8ac6881909a9e96e0873a3ae2 |
completed | April 28, 2026, 9:34 p.m. |
Created at: April 16, 2026, 8:23 p.m.