Triple
T32931052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CFLI Country Pilots |
E842398
|
entity |
| Predicate | typeOfFundingMobilized |
P67
|
FINISHED |
| Object | private capital |
—
|
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: private capital | Statement: [CFLI Country Pilots, typeOfFundingMobilized, private capital]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfFundingMobilized Context triple: [CFLI Country Pilots, typeOfFundingMobilized, private capital]
-
A.
raisedMoneyFor
Indicates that one entity collected or obtained funds specifically to support or benefit another entity, cause, or purpose.
-
B.
fundFinancedBy
Indicates that a particular fund receives its financial resources or backing from a specified source or entity.
-
C.
fundingLevel
Indicates the amount or degree of financial resources allocated or committed to an entity, project, or activity.
-
D.
fundedBy
chosen
Indicates that an entity receives financial support or resources from another entity.
-
E.
approximateUSFunding
Indicates an estimated or rough amount of financial support provided by the United States to a given entity or activity.
- 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_69f34948adfc8190a937f1f622783c0b |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_6a00868083b081909afc3d8d4ad56b43 |
completed | May 10, 2026, 1:22 p.m. |
| PD | Predicate disambiguation | batch_6a0084f5f72c8190b08afa82690e322a |
completed | May 10, 2026, 1:15 p.m. |
Created at: May 1, 2026, 1:20 a.m.