Triple
T4806236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Air Force Security Service network |
E106953
|
entity |
| Predicate | typeOfSignal |
P4618
|
FINISHED |
| Object | electronic communications |
—
|
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: electronic communications | Statement: [United States Air Force Security Service network, typeOfSignal, electronic communications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfSignal Context triple: [United States Air Force Security Service network, typeOfSignal, electronic communications]
-
A.
signalType
chosen
Indicates the specific kind or category of signal associated with or used by an entity or interaction.
-
B.
searchesSignalType
Indicates that an entity actively looks for or queries a specific type or category of signal.
-
C.
callSignType
Indicates the classification or category of a call sign associated with an entity or communication.
-
D.
signalProperty
Indicates that one entity has a specific characteristic, attribute, or feature related to a signal.
-
E.
typeOfCommand
Indicates that one entity is a specific kind or category of command in relation to 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_69bd43f6a1e08190bf0a372bfc336ee5 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c1c43a48190a65e56b1624a2339 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:23 p.m.