Triple
T21980988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hit the Deck |
E542837
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Debbie Reynolds |
—
|
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: Debbie Reynolds | Statement: [Hit the Deck, starring, Debbie Reynolds]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Debbie Reynolds Context triple: [Hit the Deck, starring, Debbie Reynolds]
-
A.
Debbie Reynolds
chosen
Debbie Reynolds was an American actress, singer, and dancer best known for her roles in classic Hollywood musicals such as "Singin' in the Rain."
-
B.
Heidi Hutton
Heidi Hutton is the daughter of American actor Jim Hutton, known for his film and television roles in the 1960s and 1970s.
-
C.
Loretta Young
Loretta Young was an American film and television actress known for her elegance, prolific career in Hollywood’s Golden Age, and Academy Award–winning performance in "The Farmer’s Daughter."
-
D.
Lala Kent
Lala Kent is an American reality television personality, actress, and entrepreneur best known for her role on Bravo's "Vanderpump Rules."
-
E.
Ann Sheridan
Ann Sheridan was an American film actress and singer of the 1930s and 1940s, nicknamed "The Oomph Girl" for her sultry screen presence in numerous Hollywood classics.
- 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_69e0c48136b081908831fa907cc02e18 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1248cf0388190b557d065beb662b5 |
completed | April 28, 2026, 9:20 p.m. |
Created at: April 16, 2026, 8:04 p.m.