Triple
T19875989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rodney A. Grant |
E477637
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Rodney A. Grant |
—
|
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: Rodney A. Grant | Statement: [Rodney A. Grant, name, Rodney A. Grant]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rodney A. Grant Context triple: [Rodney A. Grant, name, Rodney A. Grant]
-
A.
Rodney A. Grant
chosen
Rodney A. Grant is a Native American actor best known for his role as the Sioux warrior Wind In His Hair in the film "Dances with Wolves."
-
B.
Rodney S. Young
Rodney S. Young was an American archaeologist best known for his pioneering excavations at the ancient Phrygian capital of Gordion in modern-day Turkey.
-
C.
Jeffrey S. Mearns
Jeffrey S. Mearns is an American academic leader and attorney who serves as the president of Ball State University in Indiana.
-
D.
Rodney D. Smith
Rodney D. Smith is an academic leader who has served as president of the University of The Bahamas.
-
E.
Philip J. Purcell
Philip J. Purcell is an American business executive and Notre Dame alumnus best known as the former CEO of Morgan Stanley.
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658db058c8190b7bf0b003ead5bfc |
completed | April 20, 2026, 4:48 p.m. |
Created at: April 10, 2026, 1:52 p.m.