Triple
T2605500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Policy Unit (Prime Minister's Office, UK) |
E58647
|
entity |
| Predicate | typeOfStaff |
P11881
|
FINISHED |
| Object | policy advisers |
—
|
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: policy advisers | Statement: [Policy Unit (Prime Minister's Office, UK), typeOfStaff, policy advisers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfStaff Context triple: [Policy Unit (Prime Minister's Office, UK), typeOfStaff, policy advisers]
-
A.
personnelType
chosen
Indicates the classification or role category assigned to a person within an organization or system.
-
B.
typeOfRole
Indicates that one entity specifies the kind or category of role that another entity holds or performs.
-
C.
departmentType
Indicates the classification or category of a department, specifying what kind of department it is.
-
D.
crewType
Indicates the specific role or category of crew associated with an entity, such as the type of personnel assigned to operate or support it.
-
E.
designationType
Indicates the specific category or kind of formal status, title, or label that has been assigned in a designation relationship.
- 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_69ab4ac3523881909679750c9f8c2dec |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd8def9bc8190b2e013abffc7b191 |
completed | March 7, 2026, 7:50 a.m. |
| PD | Predicate disambiguation | batch_69abd80ab7248190ba06ba14fe4c5638 |
completed | March 7, 2026, 7:47 a.m. |
Created at: March 6, 2026, 9:49 p.m.