Triple
T526424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Security Letter |
E10927
|
entity |
| Predicate | gagOrderRestricts |
P10734
|
FINISHED |
| Object | disclosure of NSL existence |
—
|
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: disclosure of NSL existence | Statement: [National Security Letter, gagOrderRestricts, disclosure of NSL existence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: gagOrderRestricts Context triple: [National Security Letter, gagOrderRestricts, disclosure of NSL existence]
-
A.
canOrder
Indicates that one entity has the ability or permission to place an order for another entity or item.
-
B.
notableRestriction
chosen
Indicates that there is a significant limitation, constraint, or prohibition that meaningfully affects the entity or its use.
-
C.
hasOrder
Indicates that one entity possesses, is associated with, or is characterized by a specific order, sequence, or arrangement relative to others.
-
D.
orderType
Indicates the specific category or classification of an order, such as its purpose, channel, or processing method.
-
E.
orderingGuarantee
Indicates that there is a constraint on the relative order in which related events, operations, or messages must occur or be observed.
- 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_69a2e84b16c4819088d284c47c3a7968 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f1d0d22081908aad915482d39e74 |
completed | Feb. 28, 2026, 1:46 p.m. |
| PD | Predicate disambiguation | batch_69a2f0198ecc8190883849e5a8245963 |
completed | Feb. 28, 2026, 1:39 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.