Triple
T18041392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Independent Safeguarding Authority |
E431660
|
entity |
| Predicate | typeOfVetting |
P129570
|
FINISHED |
| Object | safeguarding vetting |
—
|
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: safeguarding vetting | Statement: [Independent Safeguarding Authority, typeOfVetting, safeguarding vetting]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfVetting Context triple: [Independent Safeguarding Authority, typeOfVetting, safeguarding vetting]
-
A.
typeOfTrust
Indicates the specific kind or category of trust that characterizes the relationship between entities.
-
B.
degreeOfAttestation
Indicates the extent or level to which something (such as a claim, form, or document) is supported, verified, or confirmed by evidence or authoritative sources.
-
C.
typeOfAudit
Indicates the specific category or kind of audit being performed or referenced in relation to an entity.
-
D.
candidateVettingBy
Indicates that a candidate is being evaluated, screened, or vetted by a specified person, group, or process.
-
E.
dataTypeVerified
Indicates that the data’s type has been checked and confirmed to match the expected or required type.
- 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_69d8b906482481908183315b9ecf9994 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4bfee78048190b3fada0eb3d28c77 |
completed | April 19, 2026, 11:43 a.m. |
| PD | Predicate disambiguation | batch_69e3f908da508190a088aa837ea5b7af |
completed | April 18, 2026, 9:35 p.m. |
| PDg | Predicate description generation | batch_69e42d8eefa88190a700c7c1b4213e46 |
completed | April 19, 2026, 1:19 a.m. |
Created at: April 10, 2026, 10:25 a.m.