Triple
T17849142
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael B. Jordan |
E445748
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Donna Jordan |
—
|
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: Donna Jordan | Statement: [Michael B. Jordan, mother, Donna Jordan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Donna Jordan Context triple: [Michael B. Jordan, mother, Donna Jordan]
-
A.
Donna Jordan
chosen
Donna Jordan is best known as the mother of acclaimed American actor and filmmaker Michael B. Jordan.
-
B.
Kathy Jordan
Kathy Jordan is best known as the former wife of American civil rights activist and Baptist minister Al Sharpton.
-
C.
Donna Stone
Donna Stone is the caring, resourceful suburban mother and central figure of the classic American television sitcom "The Donna Reed Show."
-
D.
Donna Diamond
Donna Diamond is an American illustrator best known for creating evocative cover art for classic children's and young adult novels.
-
E.
Sandra Davenport
Sandra Davenport is the first wife of American actor and comedian Jim Belushi, with whom she has one son.
- 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_69d8b9f26f18819089c9e43250bee6ae |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48ffd7e2c81909a42cc7ab64e7db9 |
completed | April 19, 2026, 8:19 a.m. |
Created at: April 10, 2026, 10:16 a.m.