Triple
T5242951
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ossian Sweet |
E118387
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Ossian Sweet |
E118387
|
NE FINISHED |
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: Ossian Sweet | Statement: [Ossian Sweet, name, Ossian Sweet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ossian Sweet Context triple: [Ossian Sweet, name, Ossian Sweet]
-
A.
Ossian Sweet
chosen
Ossian Sweet was an African American physician whose 1925 trial for defending his Detroit home against a white mob became a landmark civil rights case.
-
B.
Ossian Kelly Ingram
Ossian Kelly Ingram was a U.S. Navy sailor and Medal of Honor recipient from World War I, commemorated for his bravery and sacrifice.
-
C.
OJ Haywood
OJ Haywood is the quiet, determined horse rancher protagonist of Jordan Peele’s sci-fi horror film "Nope."
-
D.
Gulian McEvers
Gulian McEvers was an early American merchant and broker in New York City who was among the original founders of what became the New York Stock Exchange.
-
E.
John Mungo Grant
John Mungo Grant is one of the children of British actor Hugh Grant.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69bd4468aacc8190a8196f71855cdf4f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7b4da7308190856cdcee9cca41eb |
completed | March 20, 2026, 4:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bef82b42308190b9e3e0e113d8093b |
completed | March 21, 2026, 7:57 p.m. |
Created at: March 20, 2026, 1:49 p.m.