Triple
T22029441
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lump-Sum Death Payment |
E544046
|
entity |
| Predicate | statutoryTerm |
P32366
|
FINISHED |
| Object | lump-sum death payment |
—
|
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: lump-sum death payment | Statement: [Lump-Sum Death Payment, statutoryTerm, lump-sum death payment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: statutoryTerm Context triple: [Lump-Sum Death Payment, statutoryTerm, lump-sum death payment]
-
A.
isStatutory
Indicates that something exists, applies, or is defined by virtue of formal law or statute rather than by custom, contract, or other sources.
-
B.
statutoryType
chosen
Indicates the specific legal or statutory category under which something is formally classified or regulated.
-
C.
fixedTerm
Indicates that the relationship, agreement, or condition applies for a predetermined, non-variable duration of time.
-
D.
termOfProtection
Indicates the duration or conditions under which a right, protection, or legal safeguard remains in force.
-
E.
termFixedBy
Indicates that a term is determined, constrained, or made unchangeable by another entity or condition.
- 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_69e11e2f98c8819083e11eab90942a78 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f127ebf6d48190b84e7a45bbf9049c |
completed | April 28, 2026, 9:34 p.m. |
| PD | Predicate disambiguation | batch_69e6f63b0d048190b241622759aab9de |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:24 p.m.