Triple
T20804692
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FMAP |
E512124
|
entity |
| Predicate | dataSourceForFormula |
P31182
|
FINISHED |
| Object | Bureau of Economic Analysis income data |
—
|
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: Bureau of Economic Analysis income data | Statement: [FMAP, dataSourceForFormula, Bureau of Economic Analysis income data]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataSourceForFormula Context triple: [FMAP, dataSourceForFormula, Bureau of Economic Analysis income data]
-
A.
dataSourceFor
Indicates that one entity serves as the origin or provider of data that is used or consumed by another entity.
-
B.
dataSourceForApportionment
Indicates that one entity serves as the source of data used to determine or calculate the apportionment of another entity.
-
C.
formulaType
Indicates the specific kind or category of formula associated with an entity or expression.
-
D.
fieldEquationsSource
chosen
Indicates that one entity serves as the source or origin from which the field equations of another entity are derived or obtained.
-
E.
usedByDataProvider
Indicates that something (such as a resource, tool, or method) is utilized or consumed by a data provider in the course of supplying or managing data.
- 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_69e0b4cc69f481908e98751e697b9df4 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2ce6420819091792ffaa3c46c53 |
completed | April 21, 2026, 12:20 a.m. |
| PD | Predicate disambiguation | batch_69e5c99ca55481908e8d434fa901cfd6 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:40 p.m.