Triple
T23017662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Murder, My Sweet |
E573075
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | John Paxton |
—
|
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: John Paxton | Statement: [Murder, My Sweet, screenwriter, John Paxton]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Paxton Context triple: [Murder, My Sweet, screenwriter, John Paxton]
-
A.
John Paxton
chosen
John Paxton was an American screenwriter known for his acclaimed adaptations of literary works and his contributions to mid-20th-century Hollywood cinema.
-
B.
Tom McKissick
Tom McKissick is an individual notable enough to be recognized as a prominent bearer of the McKissick surname.
-
C.
Ron Fannin
Ron Fannin is a notable individual who shares the surname Fannin, recognized as a bearer of that family name.
-
D.
Steuart Pittman
Steuart Pittman is a Maryland politician who serves as the county executive of Anne Arundel County, focusing on issues such as responsible development, environmental protection, and public services.
-
E.
Paul Bransom
Paul Bransom was an American illustrator and wildlife artist best known for his detailed animal drawings in early 20th-century books and magazines.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e64a4c8190b8d29ed638c7fef8 |
completed | April 29, 2026, 4:07 a.m. |
Created at: April 17, 2026, 3:52 p.m.