Triple
T16399629
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PAYE tax system |
E398276
|
entity |
| Predicate | basisOfDeduction |
P7051
|
FINISHED |
| Object | PAYE tax code |
—
|
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: PAYE tax code | Statement: [PAYE tax system, basisOfDeduction, PAYE tax code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: basisOfDeduction Context triple: [PAYE tax system, basisOfDeduction, PAYE tax code]
-
A.
decisionBasis
Indicates the underlying reason, criterion, or rationale on which a decision is made.
-
B.
usedAsBasisFor
chosen
Indicates that one entity serves as the foundation, reference, or starting point upon which another entity is developed, derived, justified, or constructed.
-
C.
basedOnBy
Indicates that one entity is derived from, justified by, or constructed using another entity as its source, foundation, or reference.
-
D.
basedOnFactFrom
Indicates that something is derived, justified, or constructed using factual information obtained from a specified source.
-
E.
basingConcept
Indicates that one concept serves as the foundational basis or underlying rationale for another concept.
- 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_69d87f2950248190bc8ad9b9bebdc8c8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e327cea4e481908400b852a5a7032a |
completed | April 18, 2026, 6:42 a.m. |
| PD | Predicate disambiguation | batch_69e226fe1dd08190865c181721f8c348 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:09 a.m.