Triple
T6156740
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Nations Security Management System |
E137339
|
entity |
| Predicate | policyBasis |
P69503
|
FINISHED |
| Object | duty of care of the United Nations towards its personnel |
—
|
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: duty of care of the United Nations towards its personnel | Statement: [United Nations Security Management System, policyBasis, duty of care of the United Nations towards its personnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: policyBasis Context triple: [United Nations Security Management System, policyBasis, duty of care of the United Nations towards its personnel]
-
A.
legalBasis
Indicates the legal rule, authority, or justification under which an action, decision, or status is established or carried out.
-
B.
policyName
Indicates the specific name or title assigned to a policy associated with an entity.
-
C.
policyElement
Indicates that something is a component or constituent part of a broader policy.
-
D.
policyCategory
Indicates the classification or type of policy under which an item, rule, or action is grouped.
-
E.
decisionBasis
Indicates the underlying reason, criterion, or rationale on which a decision is made.
- F. None of above. chosen
Provenance (4 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_69c008a45d008190832a9e19f5d63406 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05d3177588190970a45af0d43b04c |
completed | March 22, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69c055f39e0881909ae56444b1b48929 |
completed | March 22, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69c056c87340819088003f427706ebf8 |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:17 p.m.