Triple
T18859155
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Douglas |
E461262
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Sarah Douglas |
—
|
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: Sarah Douglas | Statement: [Sarah Douglas, name, Sarah Douglas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Douglas Context triple: [Sarah Douglas, name, Sarah Douglas]
-
A.
Sarah Douglas
chosen
Sarah Douglas is a British actress best known for her villainous roles in fantasy and science fiction films, including General Zod’s ally Ursa in the Superman movies and the sorceress Queen Taramis in Conan the Destroyer.
-
B.
Shirley Douglas
Shirley Douglas was a Canadian actress and activist known for her work in film, television, and theatre, as well as for her prominent political and social advocacy.
-
C.
Christa Campbell
Christa Campbell is an American actress-turned-film producer known for her work on genre films and mainstream action movies.
-
D.
Grace Sheffield
Grace Sheffield is the youngest, intellectually precocious daughter in the wealthy Sheffield family on the sitcom "The Nanny."
-
E.
Ruby Campbell
Ruby Campbell was the wife of British speed record breaker Donald Campbell, known primarily for her association with his high-profile racing career.
- 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_69d8dcfb7b9c8190854e7b171b98ea2e |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c05eaee881909da704cf1374158c |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 10, 2026, 11:57 a.m.