Triple
T11864405
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Working Tax Credit |
E282244
|
entity |
| Predicate | dataUsedForAssessment |
P51624
|
FINISHED |
| Object | previous tax year income |
—
|
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: previous tax year income | Statement: [Working Tax Credit, dataUsedForAssessment, previous tax year income]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataUsedForAssessment Context triple: [Working Tax Credit, dataUsedForAssessment, previous tax year income]
-
A.
assessmentNumber
Indicates the unique identifier or code assigned to a specific assessment instance or record.
-
B.
standardizedAssessment
Indicates that an entity is evaluated using a uniform, systematically designed assessment administered and scored in a consistent manner across all subjects or contexts.
-
C.
assessmentMethod
Indicates the method or procedure used to evaluate, measure, or judge something.
-
D.
assessmentBasis
chosen
Indicates the underlying criteria, evidence, or method used as the foundation for making an assessment or evaluation between entities.
-
E.
typeOfAssessmentInfluenced
Indicates that one entity has an effect on or shapes the kind of assessment applied to another entity.
- 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_69d6ab2945d081908a5851c916cbcfb5 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a73883508190a78b5f4ba4a220df |
completed | April 10, 2026, 7:31 a.m. |
| PD | Predicate disambiguation | batch_69d8a2573dbc8190ab432e8e28fde6cc |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.