Triple
T20362640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Audrey Meadows |
E496819
|
entity |
| Predicate | workedWith |
P398
|
FINISHED |
| Object | Joyce Randolph |
—
|
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: Joyce Randolph | Statement: [Audrey Meadows, workedWith, Joyce Randolph]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joyce Randolph Context triple: [Audrey Meadows, workedWith, Joyce Randolph]
-
A.
Joyce Randolph
chosen
Joyce Randolph is an American actress best known for playing Trixie Norton on the classic 1950s television sitcom "The Honeymooners."
-
B.
Judy Lewis
Judy Lewis was an American actress and television producer best known as the secret daughter of Hollywood stars Loretta Young and Clark Gable.
-
C.
Gena Lee Nolin
Gena Lee Nolin is an American actress and model best known for her role as Neely Capshaw on the television series Baywatch.
-
D.
Dorothy Malone
Dorothy Malone was an American film and television actress best known for her Oscar-winning role in "Written on the Wind" and her later work on the TV series "Peyton Place."
-
E.
Lois Nettleton
Lois Nettleton was an American actress known for her versatile work in film, television, and theater from the 1950s through the 1990s.
- 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_69e0b4a3f7f48190b37f354574028ca6 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6786efd2c8190821932ddcdef1a2f |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:26 a.m.