Triple
T17946740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Read |
E448721
|
entity |
| Predicate | appearsIn |
P795
|
FINISHED |
| Object | Arthur |
—
|
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 | Statement: [David Read, appearsIn, Arthur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Arthur Context triple: [David Read, appearsIn, Arthur]
-
A.
Arthur
Arthur is a skilled point man and strategist in the film "Inception," known for his meticulous planning and execution of shared dream heists alongside Dom Cobb.
-
B.
Arthur
Arthur is a central character, likely a leader or protagonist, around whom allies such as Goosefat Bill rally in a shared cause or conflict.
-
C.
Arthur
Arthur is the given name of Arthur Chevrolet, a Swiss-American race car driver and early automotive pioneer.
-
D.
Arthur
Arthur is the first name of American professional golfer Art Wall Jr., best known for winning the 1959 Masters Tournament.
-
E.
Arthur
Arthur is the birth name of the Brazilian football legend widely known as Zico, one of the greatest attacking midfielders in the sport’s history.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide. chosen
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_69d8b9f8cca8819099836916c56b7c95 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4ad99df408190a8a4e3d21c03fe71 |
completed | April 19, 2026, 10:25 a.m. |
Created at: April 10, 2026, 10:21 a.m.