Triple
T30893287
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katharine Gun |
E786957
|
entity |
| Predicate | leakedDocumentFrom |
P86580
|
FINISHED |
| Object | National Security Agency |
—
|
NE NERFINISHED |
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: National Security Agency | Statement: [Katharine Gun, leakedDocumentFrom, National Security Agency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leakedDocumentFrom Context triple: [Katharine Gun, leakedDocumentFrom, National Security Agency]
-
A.
leakedDocumentsPublishedBy
Indicates that leaked documents were made publicly available by a particular publisher or entity.
-
B.
leakedFrom
chosen
Indicates that information, material, or content has been disclosed or escaped from a particular source, typically without authorization.
-
C.
documentLeak
Indicates that a document has been disclosed or exposed to unauthorized parties, typically without permission or intended confidentiality.
-
D.
documentedBy
Indicates that something is recorded, described, or evidenced in a specific document or set of documents.
-
E.
documentSource
Indicates that one entity serves as the origin, provider, or provenance source for a given document.
- 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_69f224bbfa7c81908448e0c261c523e3 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f692391694819096143e91732b126b |
completed | May 3, 2026, 12:09 a.m. |
| PD | Predicate disambiguation | batch_69f68b7ec098819080480998038de940 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 29, 2026, 8:49 p.m.