Triple
T22282680
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sundown Trail |
E550773
|
entity |
| Predicate | hasCastMember |
P2308
|
FINISHED |
| Object | Charles King |
—
|
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: Charles King | Statement: [Sundown Trail, hasCastMember, Charles King]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles King Context triple: [Sundown Trail, hasCastMember, Charles King]
-
A.
Charles King
Charles King was an American academic and politician who served as the ninth president of Columbia College (now Columbia University) in the mid-19th century.
-
B.
Charles King
Charles King was a member of the King family that included Leslie Lynch King Sr., the biological father of U.S. President Gerald Ford.
-
C.
Charles King
Charles King is a film editor known for his work on major Hollywood productions, including Star Wars: Episode III – Revenge of the Sith.
-
D.
Charles King
chosen
Charles King was an American actor active in early 20th-century film and theater, known for his roles in numerous silent and early sound movies.
-
E.
Charles King
Charles King was an American media executive best known for founding King World Productions, the company that distributed popular television programs such as "Wheel of Fortune" and "Jeopardy!".
- 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_69e11e44d538819097c6b8f333af3352 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f14eacd6cc8190812c6f672641050e |
completed | April 29, 2026, 12:19 a.m. |
Created at: April 16, 2026, 8:40 p.m.