Triple
T12613412
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Big House |
E301184
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object | Karl Dane |
E302404
|
NE FINISHED |
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: Karl Dane | Statement: [The Big House, castMember, Karl Dane]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karl Dane Context triple: [The Big House, castMember, Karl Dane]
-
A.
Karl Dane
chosen
Karl Dane was a Danish-American silent film actor best known for his comic roles in 1920s Hollywood, particularly as part of the popular screen duo "Dane & Arthur."
-
B.
Karl Olive
Karl Olive is a French politician and former sports journalist who has served as a mayor and later became a member of the National Assembly.
-
C.
Karl VanDevender
Karl VanDevender is an American physician best known as the husband of acclaimed novelist Ann Patchett.
-
D.
Karl Ferris
Karl Ferris is a British photographer best known for his pioneering psychedelic imagery on 1960s rock album covers, particularly for Jimi Hendrix.
-
E.
Karl Brown
Karl Brown was an early American cinematographer and filmmaker known for his pioneering work in the motion picture industry and involvement in establishing professional standards for cinematography.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d7bdeaf49c8190b13800111fa77ea3 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d960c2e5b88190a7cc16002b218d8a |
completed | April 10, 2026, 8:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d5ea02e08190b3be1fdfe86b4ee5 |
completed | May 3, 2026, 4:58 a.m. |
Created at: April 9, 2026, 5:12 p.m.