Triple
T25238049
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heath government |
E632389
|
entity |
| Predicate | employmentSecretary |
P4395
|
FINISHED |
| Object | Robert Carr |
—
|
NE NERFINISHED |
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: Robert Carr | Statement: [Heath government, employmentSecretary, Robert Carr]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employmentSecretary Context triple: [Heath government, employmentSecretary, Robert Carr]
-
A.
employerService
Indicates that one entity provides employment-related services or functions to another entity, typically in the role of an employer.
-
B.
employmentAction
Indicates an action or event that changes, initiates, or terminates an employment relationship between entities.
-
C.
employedPeople
Indicates that there exists a relationship where people are currently working in jobs or positions, typically under an employer.
-
D.
serviceSecretary
chosen
Indicates that one entity serves in the role of secretary for another entity.
-
E.
employment
Indicates a relationship where one entity hires, contracts, or otherwise engages another to perform work or services, typically in exchange for compensation.
- 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_69e75a8ec5f88190b9eba06ae42b413a |
completed | April 21, 2026, 11:07 a.m. |
| NER | Named-entity recognition | batch_69f5f6baf2d48190a6a4cd6501be87d2 |
completed | May 2, 2026, 1:06 p.m. |
| PD | Predicate disambiguation | batch_69f5afd5baac8190bb8ed576813c8591 |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 21, 2026, 1:07 p.m.