Triple
T3577548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Security Council Intelligence Directive 9 |
E75723
|
entity |
| Predicate | governsTypeOfActivity |
P20949
|
FINISHED |
| Object | signals intelligence collection |
—
|
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: signals intelligence collection | Statement: [National Security Council Intelligence Directive 9, governsTypeOfActivity, signals intelligence collection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: governsTypeOfActivity Context triple: [National Security Council Intelligence Directive 9, governsTypeOfActivity, signals intelligence collection]
-
A.
settingOfActivities
Indicates that a particular place or context serves as the environment in which certain activities occur or are carried out.
-
B.
activityType
Indicates the specific kind or category of action or event that an entity is engaged in or associated with.
-
C.
hasActivityType
chosen
Indicates the specific kind or category of activity associated with an entity or event.
-
D.
typicalActivity
Indicates that an entity is commonly or characteristically engaged in a particular activity.
-
E.
governsAspectOf
Indicates that one entity exercises control, regulation, or determining influence over a particular aspect or component of another entity.
- 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_69ad85d5e3008190bdfe0bacdd1f5a1b |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0dd3e048190a0c6666e13ead9cd |
completed | March 8, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69adb83810c481909c645c08b978edc1 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:21 p.m.