Triple
T20819871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dominion |
E512543
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Luke Allen-Gale |
—
|
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: Luke Allen-Gale | Statement: [Dominion, castMember, Luke Allen-Gale]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Luke Allen-Gale Context triple: [Dominion, castMember, Luke Allen-Gale]
-
A.
Luke Allen-Gale
chosen
Luke Allen-Gale is a British actor known for his roles in television series such as "Dominion" and "The Borgias," as well as various film and voice-acting projects.
-
B.
Douglas Gamley
Douglas Gamley was an Australian-born composer and arranger best known for his film scores and orchestral arrangements in mid-20th-century British cinema.
-
C.
Allen Davey
Allen Davey was an American cinematographer active in early Hollywood filmmaking.
-
D.
Geoff Willis
Geoff Willis is a prominent Formula One engineer known for his aerodynamic and technical leadership roles at several top teams, including Mercedes.
-
E.
Lewis Goodall
Lewis Goodall is a British journalist and broadcaster known for his political reporting and co-hosting high-profile news and current affairs programmes.
- 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_69e0b4ce39108190a6e8e5df4f1c8dc5 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2f6a65481909a0df78616e185e4 |
completed | April 21, 2026, 12:21 a.m. |
Created at: April 16, 2026, 12:41 p.m.