Triple
T21814415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eddie Fisher |
E538562
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Connie Stevens |
—
|
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: Connie Stevens | Statement: [Eddie Fisher, spouse, Connie Stevens]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Connie Stevens Context triple: [Eddie Fisher, spouse, Connie Stevens]
-
A.
Connie Stevens
chosen
Connie Stevens is an American actress and singer best known for her roles in 1960s film and television, including the series "Hawaiian Eye."
-
B.
Diana Lynn
Diana Lynn was an American film and television actress best known for her work in 1940s and 1950s Hollywood comedies and dramas.
-
C.
Betty Wright
Betty Wright is the wife of former U.S. House Speaker Jim Wright and served as his partner and supporter throughout his long political career.
-
D.
Betty Wright
Betty Wright was an American soul and R&B singer best known for her powerful vocals and hits like "Clean Up Woman," who became an influential figure in Miami's music scene.
-
E.
Donna Dixon
Donna Dixon is an American actress and former model known for her roles in 1980s comedies and for her long career in film and television.
- 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_69e0c473f0f8819086c9d1b4a143bd67 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f07cc8e6808190bde4d0e0981e4117 |
completed | April 28, 2026, 9:24 a.m. |
Created at: April 16, 2026, 6:54 p.m.