Triple
T19080960
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Tall Men |
E467029
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Frank Nugent |
—
|
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: Frank Nugent | Statement: [The Tall Men, screenwriter, Frank Nugent]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Nugent Context triple: [The Tall Men, screenwriter, Frank Nugent]
-
A.
John Bunting
John Bunting is an Australian serial killer known as the ringleader of the notorious "Snowtown murders" in South Australia during the 1990s.
-
B.
John J. Eagan
John J. Eagan was a New Jersey politician who served as a Democratic U.S. Representative in the early 20th century.
-
C.
Frank S. Nugent
chosen
Frank S. Nugent was an American screenwriter and former film critic best known for his influential collaborations with director John Ford on classic Westerns.
-
D.
Earl Hickey
Earl Hickey is the bumbling, well-meaning protagonist of the sitcom "My Name Is Earl," who devotes himself to making amends for his past misdeeds through a self-imposed karmic to-do list.
-
E.
George Lonegan
George Lonegan is a withdrawn American factory worker with a genuine psychic ability to communicate with the dead in the film "Hereafter."
- 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_69d8dd04f4488190b1121cc53ef2bfd6 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e2e8f8148190942cca6dd3e30caf |
completed | April 20, 2026, 8:25 a.m. |
Created at: April 10, 2026, 12:04 p.m.