Triple
T13512615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mrs Hughes |
E322675
|
entity |
| Predicate | portrayedBy |
P1507
|
FINISHED |
| Object | Phyllis Logan |
E581351
|
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: Phyllis Logan | Statement: [Mrs Hughes, portrayedBy, Phyllis Logan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Phyllis Logan Context triple: [Mrs Hughes, portrayedBy, Phyllis Logan]
-
A.
Phyllis Logan
chosen
Phyllis Logan is a Scottish actress best known for her award-winning film and television roles, including her portrayal of housekeeper Mrs. Hughes in the series "Downton Abbey."
-
B.
Phyllis Kirk
Phyllis Kirk was an American actress best known for her roles in 1950s film noir and horror, including the classic 3D film "House of Wax."
-
C.
Phyllis Ralph
Phyllis Ralph was the wife of English stage and film actor Lionel Atwill, known for his prominent roles in early 20th-century horror and mystery films.
-
D.
Phyllis de Young
Phyllis de Young was a member of the prominent de Young family associated with San Francisco journalism and philanthropy.
-
E.
Phyllis Garr
Phyllis Garr is the mother of American actress and comedian Teri Garr.
- 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_69d80766a21881909f21a1b7421d3b8a |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbaf87ca288190a147fbdb2f90985f |
completed | April 12, 2026, 2:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feb7ca3e348190a75c1dd8aec73a40 |
completed | May 9, 2026, 4:27 a.m. |
Created at: April 9, 2026, 9:44 p.m.