Triple
T6904493
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joel McCrea |
E159573
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Frances Dee |
E372261
|
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: Frances Dee | Statement: [Joel McCrea, spouse, Frances Dee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frances Dee Context triple: [Joel McCrea, spouse, Frances Dee]
-
A.
Frances Dee
chosen
Frances Dee was an American film actress of the 1930s and 1940s, known for her poised, refined screen presence in dramas and literary adaptations.
-
B.
Dorothy Shaw
Dorothy Shaw is the witty, down-to-earth brunette showgirl and best friend of Lorelei Lee in the musical comedy "Gentlemen Prefer Blondes."
-
C.
Shirley Scott
Shirley Scott was an influential American jazz organist renowned for her soulful Hammond B-3 playing and significant contributions to the soul-jazz genre.
-
D.
Charlotte Moorman
Charlotte Moorman was an avant-garde American cellist and performance artist known for her experimental collaborations and boundary-pushing multimedia performances.
-
E.
Marilyn Vance
Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
- 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_69c6883822e0819091e321526f20ae0a |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d989c13081908a2e346cde9e3a50 |
completed | March 27, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c75124cab88190a1510d77ed61c945 |
completed | March 28, 2026, 3:55 a.m. |
Created at: March 27, 2026, 2:25 p.m.