Triple
T22230337
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The River (1951 film) |
E549448
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Arthur Shields |
—
|
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: Arthur Shields | Statement: [The River (1951 film), stars, Arthur Shields]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arthur Shields Context triple: [The River (1951 film), stars, Arthur Shields]
-
A.
Arthur Shields
chosen
Arthur Shields was an Irish character actor known for his work in both stage and film, particularly in Hollywood productions of the mid-20th century.
-
B.
Larry Shields
Larry Shields was an influential early 20th-century American jazz clarinetist best known for his work with the Original Dixieland Jass Band.
-
C.
Larry Shields
Larry Shields was a businessman best known for owning the Minnesota Muskies franchise in the American Basketball Association.
-
D.
William Shields
William Shields is a personal name shared by multiple notable individuals across fields such as music, politics, and the military.
-
E.
Blake Shields
Blake Shields is an American actor known for his roles in television series such as Sleeper Cell and other drama and science fiction shows.
- 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_69e11e4102b881909cf47d3768e25c19 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f12bf2a26c81908aaf614d7c75e219 |
completed | April 28, 2026, 9:51 p.m. |
Created at: April 16, 2026, 8:37 p.m.