Triple
T10494977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gavin & Stacey |
E247513
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Julia Davis |
E709203
|
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: Julia Davis | Statement: [Gavin & Stacey, starring, Julia Davis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Julia Davis Context triple: [Gavin & Stacey, starring, Julia Davis]
-
A.
Julia Davis
chosen
Julia Davis is a British comedian, actress, writer, and director known for her darkly comic television work, including creating and starring in the series "Nighty Night."
-
B.
Julia Maddon
Julia Maddon is a key supporting character in the "Need for Speed" film, serving as Tobey Marshall’s determined and resourceful ally in his quest for justice.
-
C.
Julia DeMato
Julia DeMato is an American singer and former cosmetologist best known for competing as a finalist on the second season of the television show American Idol.
-
D.
Julia Dean
Julia Dean was an American actress known for her work in early- to mid-20th-century film and theater, including a role in the classic noir drama "Nightmare Alley."
-
E.
Julia Miller
Julia Miller is the birth name of Julia Phillips, the American film producer and writer known for being the first female producer to win an Academy Award for Best Picture.
- 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_69d381c309b88190af78aa681cf6a4c2 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d5098be488819083d614f528cd82fb |
completed | April 7, 2026, 1:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d90dd040f48190a645ebd131f9205c |
completed | April 10, 2026, 2:48 p.m. |
Created at: April 6, 2026, 12:24 p.m.