Triple
T30583124
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Internal security courts |
E778435
|
entity |
| Predicate | dueProcessSafeguards |
P132546
|
FINISHED |
| Object | restricted |
—
|
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: restricted | Statement: [Internal security courts, dueProcessSafeguards, restricted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dueProcessSafeguards Context triple: [Internal security courts, dueProcessSafeguards, restricted]
-
A.
governedByDueProcess
chosen
Indicates that an action or decision is carried out in accordance with established legal procedures and protections required by due process.
-
B.
underSafeguardsOf
Indicates that one entity is protected, regulated, or controlled by the safety measures, oversight, or protective mechanisms established by another entity.
-
C.
laterProtects
Indicates that one entity provides protection for another entity at a later point in time than some referenced event or protection.
-
D.
protectsFromArrest
Indicates a relationship where one party provides legal or practical protection that prevents another party from being arrested.
-
E.
safeguard
Indicates taking protective actions to shield someone or something from harm, loss, or danger.
- 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_69f224a04b248190b0ca443ec86207b8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68945093481909c6eba86bc50870e |
completed | May 2, 2026, 11:31 p.m. |
| PD | Predicate disambiguation | batch_69f67e42d6688190b60e91d2c388c555 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 8:23 p.m.