Triple
T933770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United Nations General Assembly resolutions |
E20150
|
entity |
| Predicate | mayRecommend |
P2811
|
FINISHED |
| Object | collective measures |
—
|
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: collective measures | Statement: [United Nations General Assembly resolutions, mayRecommend, collective measures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayRecommend Context triple: [United Nations General Assembly resolutions, mayRecommend, collective measures]
-
A.
canRecommend
chosen
Indicates that one entity is able or authorized to suggest or endorse another entity as suitable or preferable.
-
B.
implementsRecommendationOf
Indicates that one entity carries out or puts into practice a recommendation that was proposed or issued by another entity.
-
C.
mayRequest
Indicates that one entity is permitted or authorized to make a request to another entity or for a particular resource or action.
-
D.
couldConsider
Indicates that one entity has the potential or option to take another entity into account when making a decision, judgment, or evaluation.
-
E.
notRecommendedBy
Indicates that one entity explicitly advises against or does not endorse another 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_69a493af3dc48190adb7263e6e445ea1 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b3bcad2481908b83575b2fb80d14 |
completed | March 1, 2026, 9:46 p.m. |
| PD | Predicate disambiguation | batch_69a4b299c4d881908a57ac2711676cd7 |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.