Triple
T34008979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Politics of Jamaica |
E872049
|
entity |
| Predicate | commonPolicyIssues |
P17965
|
FINISHED |
| Object | crime and security |
—
|
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: crime and security | Statement: [Politics of Jamaica, commonPolicyIssues, crime and security]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commonPolicyIssues Context triple: [Politics of Jamaica, commonPolicyIssues, crime and security]
-
A.
commonPolicyArea
chosen
Indicates that two entities share the same policy domain, topic, or area of regulatory or legislative focus.
-
B.
politicalIssueIn
Indicates that a political issue is relevant to, occurs within, or is associated with a particular geographic or political region.
-
C.
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.
-
D.
socialConcern
Indicates a relationship where an entity is concerned about, attentive to, or actively engaged with social issues, problems, or well-being.
-
E.
policyTopic
Indicates that one entity is about, concerned with, or categorized under a particular policy-related subject or theme.
- 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_69f349a08848819084b348d64c1879c3 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: May 1, 2026, 1:51 a.m.