Triple
T1872304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Colin Kaepernick |
E39060
|
entity |
| Predicate | protestIssue |
P13201
|
FINISHED |
| Object | racial injustice |
—
|
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: racial injustice | Statement: [Colin Kaepernick, protestIssue, racial injustice]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protestIssue Context triple: [Colin Kaepernick, protestIssue, racial injustice]
-
A.
protests
Indicates that an entity publicly expresses opposition or disapproval toward another entity, action, or situation.
-
B.
protestForm
Indicates the specific method or mode by which a protest or demonstration is carried out.
-
C.
politicalIssueIn
Indicates that a political issue is relevant to, occurs within, or is associated with a particular geographic or political region.
-
D.
politicalIssueFor
Indicates a relationship where a particular topic, problem, or policy area is considered a matter of political concern or debate for a given entity.
-
E.
socialIssue
chosen
Indicates a relationship where something is recognized or treated as a problem or concern affecting society or a community at large.
- 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_69a8862f7074819096afe7fe65e179e9 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb0f79fbc819085c54f3189a552d9 |
completed | March 7, 2026, 5 a.m. |
| PD | Predicate disambiguation | batch_69abafe2b56c81909e13d543982e6e13 |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.