Triple
T3944737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jean Marsh |
E92118
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object |
Rose Buck
Rose Buck is a central maid and housekeeper character in the British television drama series "Upstairs, Downstairs."
|
E402622
|
NE FINISHED |
How this triple was built (4 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: Rose Buck | Statement: [Jean Marsh, portrayed, Rose Buck]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rose Buck Context triple: [Jean Marsh, portrayed, Rose Buck]
-
A.
Bessie Carter
Bessie Carter is an English actress known for roles in period dramas such as "Howards End" and "Bridgerton."
-
B.
Grace Rose
Grace Rose is a painting by the Victorian English artist Frederic Sandys, known for its richly detailed Pre-Raphaelite style and evocative portrayal of a female subject.
-
C.
Antonia Van Drimmelen
Antonia Van Drimmelen is a film editor known for her work on the political drama film "Charlie Wilson's War."
-
D.
Aggie Herring
Aggie Herring was an American character actress of the silent and early sound film era, known for her supporting roles in numerous Hollywood productions.
-
E.
Jacqueline Feather
Jacqueline Feather is a screenwriter best known for her work on films such as the 1982 musical comedy "Starstruck."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rose Buck Triple: [Jean Marsh, portrayed, Rose Buck]
Generated description
Rose Buck is a central maid and housekeeper character in the British television drama series "Upstairs, Downstairs."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rose Buck Target entity description: Rose Buck is a central maid and housekeeper character in the British television drama series "Upstairs, Downstairs."
-
A.
Bessie Carter
Bessie Carter is an English actress known for roles in period dramas such as "Howards End" and "Bridgerton."
-
B.
Grace Rose
Grace Rose is a painting by the Victorian English artist Frederic Sandys, known for its richly detailed Pre-Raphaelite style and evocative portrayal of a female subject.
-
C.
Antonia Van Drimmelen
Antonia Van Drimmelen is a film editor known for her work on the political drama film "Charlie Wilson's War."
-
D.
Aggie Herring
Aggie Herring was an American character actress of the silent and early sound film era, known for her supporting roles in numerous Hollywood productions.
-
E.
Jacqueline Feather
Jacqueline Feather is a screenwriter best known for her work on films such as the 1982 musical comedy "Starstruck."
- F. None of above. chosen
Provenance (5 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_69aed965502c8190904ebad1203a4ae8 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef0d8841081908d2c1de8e5758017 |
completed | March 9, 2026, 4:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5339869fc8190aee0805a8e2deac5 |
completed | March 14, 2026, 10:08 a.m. |
| NEDg | Description generation | batch_69b5376d19bc81909dadce4a2efcd331 |
completed | March 14, 2026, 10:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b538595d2481908812ab03cdb94659 |
completed | March 14, 2026, 10:28 a.m. |
Created at: March 9, 2026, 3:24 p.m.