Triple
T31036395
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carabinieri mobile and specialized units |
E790863
|
entity |
| Predicate | isGendarmerieType |
P170689
|
FINISHED |
| Object | military police |
—
|
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: military police | Statement: [Carabinieri mobile and specialized units, isGendarmerieType, military police]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isGendarmerieType Context triple: [Carabinieri mobile and specialized units, isGendarmerieType, military police]
-
A.
isMilitaryStaffOf
Indicates that one entity serves as military personnel working for, or assigned to, another entity (such as an organization, unit, or individual).
-
B.
isMilitaryOffice
Indicates that an entity holds or is designated as a military office or official position within an armed forces structure.
-
C.
isAboutMilitaryUnit
Indicates that something (such as a document, statement, or resource) concerns, discusses, or pertains to a specific military unit.
-
D.
isMilitaryOfficer
Indicates that the subject holds an official position as an officer within a military organization.
-
E.
isMilitaryPostType
Indicates that something is classified as a type or category of military post or installation.
- F. None of above. chosen
Provenance (4 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_69f224c97a788190b5da1ead6038a74e |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f694f6c6908190906d296c5e109852 |
completed | May 3, 2026, 12:21 a.m. |
| PD | Predicate disambiguation | batch_69f690f13d7481908ddfefe95df2a1c2 |
completed | May 3, 2026, 12:04 a.m. |
| PDg | Predicate description generation | batch_69f6938244648190a553b532387b812c |
completed | May 3, 2026, 12:14 a.m. |
Created at: April 29, 2026, 8:59 p.m.