Triple
T30356462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Primary Care Trusts in the NHS in England and Wales |
E772154
|
entity |
| Predicate | numberAtPeak |
P165818
|
FINISHED |
| Object | 303 in England |
—
|
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: 303 in England | Statement: [Primary Care Trusts in the NHS in England and Wales, numberAtPeak, 303 in England]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberAtPeak Context triple: [Primary Care Trusts in the NHS in England and Wales, numberAtPeak, 303 in England]
-
A.
hasNumberAtPeak
chosen
Indicates that an entity possesses a specific numerical value measured at its highest or peak point.
-
B.
numberOfLocationsAtPeak
Indicates the total count of distinct locations associated with an entity at its highest or peak point in time or activity.
-
C.
deploymentPeakNumber
Indicates the maximum number of deployments (or deployment instances) reached during a specified period or under given conditions.
-
D.
numberOfEmployeesAtPeak
Indicates the highest recorded count of employees that an entity had at any point in time.
-
E.
populationAtPeak
Indicates that an entity’s population size is measured at its highest recorded level during a specified time or condition.
- 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_69f2248c6f5c8190a6177842bf791a3c |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a006fe981488190b4287289a3327664 |
completed | May 10, 2026, 11:45 a.m. |
| PD | Predicate disambiguation | batch_6a006f6976ec8190ba2c04fbaa946345 |
completed | May 10, 2026, 11:43 a.m. |
Created at: April 29, 2026, 7:57 p.m.