Triple
T17791658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maggie Collins |
E444176
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Kari Matchett |
—
|
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: Kari Matchett | Statement: [Maggie Collins, portrayedBy, Kari Matchett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kari Matchett Context triple: [Maggie Collins, portrayedBy, Kari Matchett]
-
A.
Kari Matchett
chosen
Kari Matchett is a Canadian actress known for her work in film and television, including prominent roles in series such as "Covert Affairs" and "24."
-
B.
Kari Holbrook
Kari Holbrook is an individual notable enough to be recognized as a prominent bearer of the Holbrook surname.
-
C.
Michelle Mylett
Michelle Mylett is a Canadian actress best known for playing Katy on the comedy series "Letterkenny."
-
D.
Danelle Morton
Danelle Morton is an American journalist and author known for co-writing celebrity memoirs and nonfiction books, including collaborating with Lynne Spears.
-
E.
Susan Karike
Susan Karike was a Papua New Guinean designer best known for creating her country's national flag.
- 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_69d8b9efe370819095cd219b143ae727 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48797408081908c48d98e1525ae87 |
completed | April 19, 2026, 7:43 a.m. |
Created at: April 10, 2026, 10:13 a.m.