Triple
T20397664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | All That Money Can Buy |
E500250
|
entity |
| Predicate | leadActor |
P1507
|
FINISHED |
| Object | Jane Darwell |
—
|
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: Jane Darwell | Statement: [All That Money Can Buy, leadActor, Jane Darwell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jane Darwell Context triple: [All That Money Can Buy, leadActor, Jane Darwell]
-
A.
Jane Darwell
chosen
Jane Darwell was an American character actress best known for her Academy Award–winning performance as Ma Joad in the film adaptation of "The Grapes of Wrath."
-
B.
Edda Winchell
Edda Winchell was the daughter of influential American newspaper and radio gossip columnist Walter Winchell.
-
C.
Agnes Moorehead
Agnes Moorehead was an American actress renowned for her powerful character roles in film, radio, and television, notably in Orson Welles’s Mercury Theatre and as Endora on the TV series "Bewitched."
-
D.
Mary Marquardt
Mary Marquardt is an American former chef and illustrator best known as Harrison Ford’s first wife, to whom he was married from 1964 to 1979.
-
E.
Dorothy Farnum
Dorothy Farnum was an American screenwriter of the silent film era, known for adapting literary works and crafting sophisticated romantic dramas for major Hollywood studios.
- 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_69e0b4a81bec8190b69adfdc1336a015 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6798c2b28819092fab93f01218cde |
completed | April 20, 2026, 7:07 p.m. |
Created at: April 16, 2026, 11:29 a.m.