Triple
T12903331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Work-Related Activity Group |
E308664
|
entity |
| Predicate | appliesToAssessmentGroup |
P1129
|
FINISHED |
| Object | limited capability for work group |
—
|
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: limited capability for work group | Statement: [Work-Related Activity Group, appliesToAssessmentGroup, limited capability for work group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToAssessmentGroup Context triple: [Work-Related Activity Group, appliesToAssessmentGroup, limited capability for work group]
-
A.
typeOfAssessmentAlignment
Indicates that an assessment is aligned with, or corresponds to, a particular standard, objective, or framework.
-
B.
assessmentName
Indicates the specific title or label assigned to an assessment within a system or context.
-
C.
assessedBy
Indicates that an entity has been evaluated, examined, or judged by another entity (typically an agent or authority).
-
D.
typeOfAssessmentInfluenced
Indicates that one entity has an effect on or shapes the kind of assessment applied to another entity.
-
E.
appliesTo
chosen
Indicates that something is relevant, valid, or has effect in relation to a particular entity, case, or context.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d971820e008190bf8bc7c392c8bcbb |
completed | April 10, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69d96fa776648190b9b5c30722ea50b6 |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:40 p.m.