Triple
T20883256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Good Lie |
E514205
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Sarah Baker |
—
|
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: Sarah Baker | Statement: [The Good Lie, starring, Sarah Baker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sarah Baker Context triple: [The Good Lie, starring, Sarah Baker]
-
A.
Sarah Baker
chosen
Sarah Baker is an American actress and comedian known for her work in television and film, including a prominent role on the Netflix series "The Kominsky Method."
-
B.
Sarah Lindsey Baker
Sarah Lindsey Baker is best known as the wife of the late American actor, lawyer, and U.S. Senator Fred Thompson.
-
C.
Anne Baker
Anne Baker is a political leader who serves as the mayor of the Isaac Region.
-
D.
Nora Baker
Nora Baker was the wartime codename of Noor Inayat Khan, a British-Indian SOE agent and wireless operator in Nazi-occupied France during World War II, celebrated for her courage and posthumously awarded the George Cross.
-
E.
Betsy Baker
Betsy Baker is an American actress best known for her role as Linda in Sam Raimi’s cult horror film "The Evil Dead."
- 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.