Triple
T26391215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Royal Berkshire NHS Foundation Trust |
E663415
|
entity |
| Predicate | trustType |
P9393
|
FINISHED |
| Object | acute and specialist services |
—
|
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: acute and specialist services | Statement: [Royal Berkshire NHS Foundation Trust, trustType, acute and specialist services]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trustType Context triple: [Royal Berkshire NHS Foundation Trust, trustType, acute and specialist services]
-
A.
typeOfTrust
chosen
Indicates the specific kind or category of trust that characterizes the relationship between entities.
-
B.
trustModel
Indicates that one entity relies on or has confidence in the reliability, integrity, or performance of another entity or system.
-
C.
trustedStatus
Indicates that one entity regards another as reliable, dependable, or worthy of confidence in a given context.
-
D.
trustPurpose
Indicates that one entity has a specific intended use, goal, or objective for which a trust or trusted arrangement is established with another entity.
-
E.
trustAnchoredVia
Indicates that a relationship of trust is established or justified through a specific intermediary or anchoring mechanism (such as a trusted authority, key, or certificate).
- 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_69ee883823988190b418b111be28a44a |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610bf1e248190a186aed862513478 |
completed | May 2, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:26 p.m.