Triple
T6519803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Committee on Safeguards |
E148351
|
entity |
| Predicate | baseLegalText |
P125
|
FINISHED |
| Object | Agreement on Safeguards |
—
|
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: Agreement on Safeguards | Statement: [Committee on Safeguards, baseLegalText, Agreement on Safeguards]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baseLegalText Context triple: [Committee on Safeguards, baseLegalText, Agreement on Safeguards]
-
A.
legalContent
Indicates that the associated material complies with applicable laws and regulations and is permitted for use, distribution, or display.
-
B.
legalBasis
chosen
Indicates the legal rule, authority, or justification under which an action, decision, or status is established or carried out.
-
C.
legalDetail
Indicates that there is specific legal information, conditions, or attributes associated with the related entity or relationship.
-
D.
legalForm
Indicates the specific legal structure or organizational type under which an entity is formally constituted and recognized by law.
-
E.
legalTermIn
Indicates that a particular legal term or concept is used, defined, or applicable within a specified legal document, jurisdiction, or context.
- 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_69c687e68e748190baceb9298f32d3ed |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6ac11d0e481908103c4b51de9521e |
completed | March 27, 2026, 4:10 p.m. |
| PD | Predicate disambiguation | batch_69c68abbc7148190a8270d47fe10cc31 |
completed | March 27, 2026, 1:48 p.m. |
Created at: March 27, 2026, 1:45 p.m.