Triple
T21229874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Boat Is Full |
E523178
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object | Curt Bois |
—
|
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: Curt Bois | Statement: [The Boat Is Full, stars, Curt Bois]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Curt Bois Context triple: [The Boat Is Full, stars, Curt Bois]
-
A.
Curt Bois
chosen
Curt Bois was a German-Jewish character actor whose long career spanned from the silent film era to notable later roles in classics like "Casablanca" and "Wings of Desire."
-
B.
Roger Dwyre
Roger Dwyre is an editor best known for his work on the film "Lady L."
-
C.
Donald Dunn
Donald Dunn was an American bass guitarist best known for his work with Booker T. & the M.G.'s and as a prominent session musician at Stax Records.
-
D.
James Coryell
James Coryell was a Texas frontiersman and early settler whose legacy is commemorated by having Coryell County, Texas, named in his honor.
-
E.
Michael Krieger
Michael Krieger is a fictional character appearing in the story of "Watch Over Me."
- 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_69e0b512ad94819087942b2ed925185f |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e734ae60408190a9480b27d109b8fc |
completed | April 21, 2026, 8:26 a.m. |
Created at: April 16, 2026, 3:45 p.m.