Triple
T20855604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Mitchell |
E513470
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Don Mitchell |
—
|
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: Don Mitchell | Statement: [Don Mitchell, name, Don Mitchell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Don Mitchell Context triple: [Don Mitchell, name, Don Mitchell]
-
A.
Don Mitchell
chosen
Don Mitchell was an American actor best known for his role as Mark Sanger, the wheelchair-bound detective’s assistant, on the television series "Ironside."
-
B.
Doug Mitchell
Doug Mitchell is a Canadian lawyer, businessman, and prominent sports executive known for his influential role in Canadian university athletics and contributions to hockey.
-
C.
Doug Mitchell
Doug Mitchell is an Australian film producer best known for his longtime collaboration with director George Miller on projects including the Mad Max franchise.
-
D.
Carl Mitchell
Carl Mitchell, better known by his stage name Twista, is a Chicago rapper renowned for his rapid-fire delivery and contributions to hip-hop.
-
E.
Carl Mitchell
Carl Mitchell is a writer associated with the German-language publication "Wetter."
- 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_69e0b4f5b01081909452f654d2fc3f50 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a81ac4819084a07625b8ed4ec5 |
completed | April 21, 2026, 12:24 a.m. |
Created at: April 16, 2026, 12:44 p.m.