Triple
T11009157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | My Gal Sal |
E260201
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Evelyn Keyes |
E322735
|
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: Evelyn Keyes | Statement: [My Gal Sal, screenwriter, Evelyn Keyes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Evelyn Keyes Context triple: [My Gal Sal, screenwriter, Evelyn Keyes]
-
A.
Evelyn Keyes
chosen
Evelyn Keyes was an American film actress best known for her role as Suellen O'Hara in the classic 1939 film "Gone with the Wind."
-
B.
Linda Harrison
Linda Harrison is an American actress best known for her role as Nova in the original "Planet of the Apes" films.
-
C.
Ora Baxter
Ora Baxter is a fictional character portrayed by actress Jane Wyman, likely featured in a mid-20th-century film or television production.
-
D.
Marjorie Main
Marjorie Main was an American character actress best known for her comedic, no-nonsense roles in classic Hollywood films, particularly as Ma Kettle in the "Ma and Pa Kettle" series.
-
E.
Dina Merrill
Dina Merrill was an American actress, heiress, and philanthropist known for her elegant screen presence in mid-20th-century Hollywood films and television.
- 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_69d6aa9687448190b28d353b1b6a610e |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7978810208190b8e2966ae67b6314 |
completed | April 9, 2026, 12:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e623e44c188190b5b83cf8f397554c |
completed | April 20, 2026, 1:02 p.m. |
Created at: April 8, 2026, 9:25 p.m.