Triple
T18073467
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Black Dakotas |
E432491
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object | Howard Wendell |
—
|
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: Howard Wendell | Statement: [The Black Dakotas, starring, Howard Wendell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Wendell Context triple: [The Black Dakotas, starring, Howard Wendell]
-
A.
Howard Wendell
chosen
Howard Wendell was an American character actor known for his supporting roles in mid-20th-century films and television, including the classic crime drama "The Big Heat."
-
B.
Patrick Wendell
Patrick Wendell is a co-founder of Databricks and a key contributor to the Apache Spark ecosystem.
-
C.
Charles Brust
Charles Brust was the husband of American film and radio actress Rochelle Hudson.
-
D.
Dan Jewett
Dan Jewett is an American science teacher known for his brief marriage to billionaire philanthropist and novelist MacKenzie Scott.
-
E.
Andy Heyward
Andy Heyward is an American television producer and executive best known for his work in children’s animation and for leading the production company DIC Entertainment.
- 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_69d8b9070cac81909fa9473fb1c3f1c7 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4ccefcdc4819086d0b224731bfc4d |
completed | April 19, 2026, 12:39 p.m. |
Created at: April 10, 2026, 10:26 a.m.