Triple
T7336543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Sharpton 2004 presidential campaign |
E169140
|
entity |
| Predicate | campaignRoleOfCandidate |
P29120
|
FINISHED |
| Object | civil rights activist |
—
|
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: civil rights activist | Statement: [Al Sharpton 2004 presidential campaign, campaignRoleOfCandidate, civil rights activist]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignRoleOfCandidate Context triple: [Al Sharpton 2004 presidential campaign, campaignRoleOfCandidate, civil rights activist]
-
A.
electoralRole
Indicates the specific function, position, or capacity an entity holds within an electoral process or system.
-
B.
partySystemRole
Indicates the specific functional role or capacity that a party assumes within a given system or context.
-
C.
electoralPosition
Indicates that an entity holds, has held, or is a candidate for a specific role or office within an electoral or political system.
-
D.
namedForPoliticalRole
Indicates that one entity is named after another entity specifically because of that entity’s political office, position, or role.
-
E.
professionOfCandidate
chosen
Indicates that one entity is the profession or occupational role held by the candidate entity.
- 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_69c68a568a6481908f11e20db7bc8446 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f347f25081908e6086d4073295f5 |
completed | March 27, 2026, 9:14 p.m. |
| PD | Predicate disambiguation | batch_69c6f028fd748190b2ea5c3081958a42 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:04 p.m.