Triple
T2721010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Foreign Intelligence Surveillance Court of Review |
E60078
|
entity |
| Predicate | mayPublish |
P41858
|
FINISHED |
| Object | redacted opinions |
—
|
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: redacted opinions | Statement: [Foreign Intelligence Surveillance Court of Review, mayPublish, redacted opinions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayPublish Context triple: [Foreign Intelligence Surveillance Court of Review, mayPublish, redacted opinions]
-
A.
mayAuthor
Indicates that an entity has the potential or permission to be the author of another entity (such as a work or document).
-
B.
maySpeak
Indicates that one entity is permitted or allowed to speak to, or communicate verbally with, another entity.
-
C.
maySign
Indicates that an entity has the permission or authority to sign a document, agreement, or similar item.
-
D.
isPublished
Indicates that an item has been formally made available to the public through some publishing process.
-
E.
publishesFor
Indicates that one entity issues, releases, or makes content publicly available on behalf of, or in service of, another entity.
- F. None of above. chosen
Provenance (4 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_69ab4b746d248190958e052045c09255 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdab1cb808190b0789c76bc9cb090 |
completed | March 7, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69abd8240920819087a812d816a55edb |
completed | March 7, 2026, 7:47 a.m. |
| PDg | Predicate description generation | batch_69abd949c120819099a9d56eb71a0339 |
completed | March 7, 2026, 7:52 a.m. |
Created at: March 6, 2026, 9:55 p.m.