Triple
T33898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNHCR |
E675
|
entity |
| Predicate | mandateIncludes |
P1393
|
FINISHED |
| Object | protection of refugees |
—
|
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: protection of refugees | Statement: [UNHCR, mandateIncludes, protection of refugees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mandateIncludes Context triple: [UNHCR, mandateIncludes, protection of refugees]
-
A.
includes
chosen
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
-
B.
isSubjectTo
Indicates that one entity is governed, affected, or constrained by the authority, rules, conditions, or influence of another entity.
-
C.
annexedBy
Indicates that one entity has been incorporated into and brought under the control or sovereignty of another entity.
-
D.
supportsPolicy
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
-
E.
requires
Indicates that one entity must exist, occur, or be satisfied before another entity can exist, occur, or be carried out.
- 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_69a2479dec388190967ba648663442c9 |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a2496ffc548190b545f998cbebd5b9 |
completed | Feb. 28, 2026, 1:48 a.m. |
| PD | Predicate disambiguation | batch_69a248717f5081909952a8c9ed1e1742 |
completed | Feb. 28, 2026, 1:44 a.m. |
Created at: Feb. 28, 2026, 1:44 a.m.