Triple
T4077899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Treaties of the United States |
E87407
|
entity |
| Predicate | mayCreate |
P5771
|
FINISHED |
| Object | international obligations for the United States |
—
|
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: international obligations for the United States | Statement: [Treaties of the United States, mayCreate, international obligations for the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayCreate Context triple: [Treaties of the United States, mayCreate, international obligations for the United States]
-
A.
mayEnter
Indicates that one entity is permitted or authorized to enter or access another entity or location.
-
B.
canMake
chosen
Indicates that one entity has the ability or capacity to create, produce, or assemble another entity.
-
C.
mayPublish
Indicates that an entity has the permission or authorization to publish another entity or piece of content.
-
D.
mayRequest
Indicates that one entity is permitted or authorized to make a request to another entity or for a particular resource or action.
-
E.
mayNot
Indicates that an entity is not permitted or is prohibited from performing a particular action or entering into a specified relationship.
- 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_69aed9435cf48190ad1da737c962d19d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefc4d348c8190a94724639830aca0 |
completed | March 9, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69aef9082c2081908474f082a49bebc8 |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:39 p.m.