Triple
T3601957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Defense Attache Service |
E76275
|
entity |
| Predicate | usesCover |
P33645
|
FINISHED |
| Object | diplomatic status for attachés |
—
|
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: diplomatic status for attachés | Statement: [Defense Attache Service, usesCover, diplomatic status for attachés]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesCover Context triple: [Defense Attache Service, usesCover, diplomatic status for attachés]
-
A.
isCoveredBy
Indicates that one entity is physically or conceptually overlaid, protected, or enclosed by another entity.
-
B.
isCoverOf
Indicates that one entity functions as a protective or enclosing layer placed over another entity.
-
C.
hasCoverType
Indicates that one entity possesses or is associated with a specific type or category of cover.
-
D.
eraCovered
Indicates that one entity temporally encompasses, includes, or spans the historical period or era associated with another entity.
-
E.
usesCoverOrganizations
chosen
Indicates that an entity operates through or makes use of front or intermediary organizations to conceal its true identity, role, or activities.
- 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_69ad85d93dcc819094fba90cf70f4996 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc1dd264c819098796f5f50f251be |
completed | March 8, 2026, 6:37 p.m. |
| PD | Predicate disambiguation | batch_69adb83b66708190bb9d2f23d6fd308e |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:22 p.m.