Triple
T18135621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liberty Valance |
E434127
|
entity |
| Predicate | opposes |
P437
|
FINISHED |
| Object | Tom Doniphon |
—
|
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: Tom Doniphon | Statement: [Liberty Valance, opposes, Tom Doniphon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Doniphon Context triple: [Liberty Valance, opposes, Tom Doniphon]
-
A.
Tom Doniphon
chosen
Tom Doniphon is a rugged, morally complex rancher portrayed by John Wayne in the classic Western film "The Man Who Shot Liberty Valance."
-
B.
Roger Donley
Roger Donley is a film editor known for his work on the animated feature "Snoopy, Come Home."
-
C.
Don Pierson
Don Pierson was an American entrepreneur best known for founding several offshore radio stations in the 1960s that challenged broadcasting monopolies in the United Kingdom.
-
D.
Vic Hoskins
Vic Hoskins is a ruthless InGen security chief in Jurassic World who seeks to weaponize dinosaurs for military use.
-
E.
Ray Blanton
Ray Blanton was an American Democratic politician who served as governor of Tennessee in the late 1970s and became notorious for a clemency scandal involving the controversial pardoning of prisoners.
- 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_69d8b909e8cc81908df4cc2b8ea6d11f |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4de0677088190aaf584882b3d74a1 |
completed | April 19, 2026, 1:52 p.m. |
Created at: April 10, 2026, 10:29 a.m.