Triple
T263657
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Insurance Contributions Act taxes |
E5806
|
entity |
| Predicate | exemptionsInclude |
P4330
|
FINISHED |
| Object | certain state and local government employees |
—
|
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: certain state and local government employees | Statement: [Federal Insurance Contributions Act taxes, exemptionsInclude, certain state and local government employees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: exemptionsInclude Context triple: [Federal Insurance Contributions Act taxes, exemptionsInclude, certain state and local government employees]
-
A.
exemptionType
chosen
Indicates the specific category or kind of exemption that applies in a given context.
-
B.
excludes
Indicates that one entity deliberately omits, leaves out, or does not allow the inclusion of another entity within a set, group, or context.
-
C.
includes
Indicates that one entity contains, encompasses, or has another entity as a part, member, or subset.
-
D.
excludesRegion
Indicates that one entity explicitly omits, leaves out, or does not apply to a specified region or geographic area.
-
E.
isSubjectTo
Indicates that one entity is governed, affected, or constrained by the authority, rules, conditions, or influence of 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_69a258dd8ea08190ac554a1cc8dfd8c3 |
completed | Feb. 28, 2026, 2:54 a.m. |
| NER | Named-entity recognition | batch_69a25d8e809881908a58c9a4e3ba07c3 |
completed | Feb. 28, 2026, 3:14 a.m. |
| PD | Predicate disambiguation | batch_69a25b6e07748190834022a65ba6d803 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:55 a.m.