Triple
T3825359
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CIA Special Activities Division |
E88672
|
entity |
| Predicate | hasSecrecy |
P13085
|
FINISHED |
| Object | highly classified |
—
|
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: highly classified | Statement: [CIA Special Activities Division, hasSecrecy, highly classified]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSecrecy Context triple: [CIA Special Activities Division, hasSecrecy, highly classified]
-
A.
hasTypeOfSecrecy
chosen
Indicates that something is associated with a particular kind or level of secrecy.
-
B.
keepsSecretAbout
Indicates that one entity intentionally withholds or conceals information regarding another specified entity or topic from others.
-
C.
hasSeclusion
Indicates that one entity provides, involves, or is characterized by a state or condition of privacy, isolation, or separation from others for another entity.
-
D.
hasSecurityDimension
Indicates that something possesses or is associated with a particular aspect or dimension of security.
-
E.
hasSecurityClass
Indicates that an entity is assigned to or associated with a particular security classification level.
- 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_69aed9538cf881909d9ce8ca4ac7c18c |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef188b474819087680db42b04ecdd |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee74a2bc081909b237df8b1e27653 |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:17 p.m.