Triple
T10737283
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keeping Mum |
E253225
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Liz Smith |
E191278
|
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: Liz Smith | Statement: [Keeping Mum, starring, Liz Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Liz Smith Context triple: [Keeping Mum, starring, Liz Smith]
-
A.
Liz Smith
chosen
Liz Smith was a beloved English character actress known for her comic roles in British television and film, including her work on the sitcom "The Vicar of Dibley."
-
B.
Susan Durant
Susan Durant was a prominent 19th-century English sculptor known for her portrait busts and association with notable Victorian figures.
-
C.
Tina Brown
Tina Brown is an American magazine editor, journalist, and author best known for revitalizing publications such as Vanity Fair and The New Yorker.
-
D.
Susanna Reid
Susanna Reid is a British television presenter and journalist best known as a long-time breakfast show host on BBC Breakfast and Good Morning Britain.
-
E.
Liz Georges
Liz Georges is known as the wife of American character actor and director David Paymer.
- 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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d710410a04819090036597ac0d271c |
completed | April 9, 2026, 2:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de22dce1cc8190a3511d86e8bd6d3e |
completed | April 14, 2026, 11:19 a.m. |
Created at: April 8, 2026, 9:14 p.m.