Triple
T16073909
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | International Security Affairs directorates within OSD |
E389933
|
entity |
| Predicate | typeOfPolicyOffice |
P18993
|
FINISHED |
| Object | regional policy office |
—
|
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: regional policy office | Statement: [International Security Affairs directorates within OSD, typeOfPolicyOffice, regional policy office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfPolicyOffice Context triple: [International Security Affairs directorates within OSD, typeOfPolicyOffice, regional policy office]
-
A.
hasOfficeType
Indicates that an entity’s office is classified as a specific type or category of office.
-
B.
governsOfficeType
Indicates that an entity has authoritative control or regulatory oversight over a particular type or category of office.
-
C.
typeOfPolicyBody
Indicates that one entity is the governing or issuing body responsible for a particular policy type.
-
D.
typeOfOffice
chosen
Indicates the specific category or kind of office that an office entity belongs to (e.g., executive, legislative, judicial, or other office types).
-
E.
officeName
Indicates the official name assigned to an office or workplace.
- 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_69d86daf32ec8190a8c0466c8f49c3c0 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1ff63edb0819092cbb671967bbdcd |
completed | April 17, 2026, 9:37 a.m. |
| PD | Predicate disambiguation | batch_69e1827ad7c88190b867da511cbfb7fa |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:57 a.m.