Triple
T27540066
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSTC-A |
E695209
|
entity |
| Predicate | usedFundingSource |
P159409
|
FINISHED |
| Object | Afghanistan Security Forces Fund |
—
|
NE NERFINISHED |
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: Afghanistan Security Forces Fund | Statement: [CSTC-A, usedFundingSource, Afghanistan Security Forces Fund]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedFundingSource Context triple: [CSTC-A, usedFundingSource, Afghanistan Security Forces Fund]
-
A.
usedFundingFrom
chosen
Indicates that one entity utilized financial resources that originated from another entity.
-
B.
usedFund
Indicates that one entity expended or applied a particular fund or financial resource for some purpose.
-
C.
usedFundingMethods
Indicates that an entity employed specific funding methods to finance an activity, project, or operation.
-
D.
usedFeederFunds
Indicates that an entity employed feeder funds as intermediary investment vehicles to channel capital into another fund or investment structure.
-
E.
creditsUse
Indicates that one entity uses or relies on credits (such as credit units, credit lines, or credit-based resources) provided or available to it.
- 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_69ef538608b081908b9f659bb09d5e0f |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f6b2a65c7c8190ac40f1466ceadefc |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14d7d508190bc7d4c89dfba4a32 |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 27, 2026, 1:30 p.m.