Triple
T20883268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Good Lie |
E514205
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Karen Kehela Sherwood |
—
|
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: Karen Kehela Sherwood | Statement: [The Good Lie, producer, Karen Kehela Sherwood]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karen Kehela Sherwood Context triple: [The Good Lie, producer, Karen Kehela Sherwood]
-
A.
Karen Kehela Sherwood
chosen
Karen Kehela Sherwood is a film producer known for her work on major Hollywood comedies and studio projects.
-
B.
Shirley Sherwood
Shirley Sherwood is a British botanist, author, and prominent collector and patron of contemporary botanical art.
-
C.
Kim Sherwood
Kim Sherwood is a British novelist and academic best known for her literary fiction and for expanding the James Bond universe with a new series of 00 novels.
-
D.
Jeannine Renshaw
Jeannine Renshaw is a television producer and writer known for her work on series such as "Good Girls."
-
E.
Laura Shavin
Laura Shavin is a British actress, comedian, and voiceover artist best known for her work on BBC Radio 4 comedy programmes.
- 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_69e0b4f733f081908a401c0b7beb0b9f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c67b03088190be7cbcde8c59509a |
completed | April 21, 2026, 12:36 a.m. |
Created at: April 16, 2026, 12:46 p.m.