Triple
T19107951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ma Jarrett |
E467707
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Jarrett |
—
|
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: Jarrett | Statement: [Ma Jarrett, familyName, Jarrett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jarrett Context triple: [Ma Jarrett, familyName, Jarrett]
-
A.
Jarrett
chosen
Jarrett is a surname most prominently associated with Valerie Jarrett, a senior advisor to former U.S. President Barack Obama and influential figure in American politics.
-
B.
Jason Jarrett
Jason Jarrett is an American former stock car racing driver who competed in NASCAR and is the son of NASCAR champion Dale Jarrett.
-
C.
Ma Jarrett
Ma Jarrett is a key supporting character in the classic 1949 film noir "White Heat," known as the fiercely devoted and manipulative mother of gangster Cody Jarrett.
-
D.
Jarrett Payton
Jarrett Payton is a former American football running back and media personality, best known as the son of NFL Hall of Famer Walter Payton.
-
E.
Garrett Clayton
Garrett Clayton is an American actor and singer best known for his roles in Disney Channel productions and musical films.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e391f00c8190881a5977dd3728ed |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:04 p.m.