Triple
T20317256
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Statutory Maternity Pay |
E510409
|
entity |
| Predicate | alternativeBenefit |
P139641
|
FINISHED |
| Object | Maternity Allowance |
—
|
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: Maternity Allowance | Statement: [Statutory Maternity Pay, alternativeBenefit, Maternity Allowance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alternativeBenefit Context triple: [Statutory Maternity Pay, alternativeBenefit, Maternity Allowance]
-
A.
exclusiveBenefit
Indicates that a benefit is provided to one party or group in a way that excludes others from receiving the same advantage.
-
B.
affectsBenefit
Indicates that one entity has an influence on, modifies, or determines the benefit or advantage received by another entity.
-
C.
relatedBenefit
Indicates that one entity provides an advantage, gain, or positive outcome that is connected or attributable to another entity.
-
D.
benefice
Indicates that one entity grants or bestows a benefit, favor, or advantage upon another.
-
E.
benefits
Indicates that one entity gains an advantage, improvement, or positive outcome as a result of another entity or action.
- F. None of above. chosen
Provenance (4 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_69e0b4c7491c8190961113c4283b10b0 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e67788ca3c8190a3496fd54a5870d6 |
completed | April 20, 2026, 6:59 p.m. |
| PD | Predicate disambiguation | batch_69e55b23a0788190bf1853ef5b81823f |
completed | April 19, 2026, 10:45 p.m. |
| PDg | Predicate description generation | batch_69e56702ad04819099c1c08f28d16809 |
completed | April 19, 2026, 11:36 p.m. |
Created at: April 16, 2026, 11:19 a.m.