Triple
T11770064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Isaiah Bradley |
E279872
|
entity |
| Predicate | raceDraftedFrom |
P27223
|
FINISHED |
| Object | African American soldiers |
—
|
LITERAL 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: African American soldiers | Statement: [Isaiah Bradley, raceDraftedFrom, African American soldiers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: raceDraftedFrom Context triple: [Isaiah Bradley, raceDraftedFrom, African American soldiers]
-
A.
draftedFrom
chosen
Indicates that one entity was selected or recruited from another entity, typically as part of a formal drafting or selection process.
-
B.
draftedInto
Indicates that an entity is formally selected or conscripted to join and serve in a particular organization, group, or role, typically without initiating the choice themselves.
-
C.
draftedUnder
Indicates that one entity was formally selected or conscripted into a role, position, or service according to the authority, rules, or jurisdiction of another entity.
-
D.
draftedFor
Indicates that one entity has been selected or assigned, typically through a draft process, to serve, play, or work for another entity.
-
E.
draftedIn
Indicates that one entity was selected or recruited into another entity (such as a team, organization, or military service) through a formal draft process.
- F. None of above.
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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a8c2e8b08190a31b1e284fca2aee |
completed | April 10, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69d8a242cd8c819086ed6c5f292dc8cb |
completed | April 10, 2026, 7:09 a.m. |
Created at: April 8, 2026, 9:41 p.m.