Triple
T15949994
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Caprica |
E386788
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Paula Malcomson |
—
|
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: Paula Malcomson | Statement: [Caprica, portrayedBy, Paula Malcomson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paula Malcomson Context triple: [Caprica, portrayedBy, Paula Malcomson]
-
A.
Paula Malcomson
chosen
Paula Malcomson is a Northern Irish actress known for her roles in television series such as Deadwood, Ray Donovan, and Sons of Anarchy, as well as films like The Hunger Games.
-
B.
Paula Throckmorton
Paula Throckmorton is an American jewelry designer and writer best known as the wife of journalist and political commentator Fareed Zakaria.
-
C.
Anita Scott
Anita Scott is known as the wife of former NBA player and coach Byron Scott.
-
D.
Paula Ridgeway
Paula Ridgeway is the central female protagonist of the novel and film "Random Harvest," whose relationship with an amnesiac man drives the story’s romantic and dramatic plot.
-
E.
Paula Wilcox
Paula Wilcox is an English actress best known for her extensive work in British television sitcoms and dramas since the 1970s.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156d4c5008190a56ebf8c28f712dc |
completed | April 16, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:53 a.m.