Triple
T20237059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Radio Broadcasting to Cuba Act |
E498176
|
entity |
| Predicate | beneficiaryPopulation |
P17586
|
FINISHED |
| Object | Cuban listeners |
—
|
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: Cuban listeners | Statement: [Radio Broadcasting to Cuba Act, beneficiaryPopulation, Cuban listeners]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: beneficiaryPopulation Context triple: [Radio Broadcasting to Cuba Act, beneficiaryPopulation, Cuban listeners]
-
A.
estimatedNumberOfBeneficiaries
Indicates the approximate count of individuals or entities expected to receive benefits from something.
-
B.
targetedPopulation
chosen
Indicates the group of individuals or entities that an action, intervention, or effect is specifically directed toward.
-
C.
beneficiaries
Indicates that certain entities receive advantages, profits, or positive outcomes from an action, event, or arrangement.
-
D.
eligibleBeneficiaries
Indicates that certain parties meet the required conditions to receive benefits or entitlements under a given rule or program.
-
E.
supportedPopulation
Indicates that one entity provides assistance, resources, or services to sustain or benefit a specified group of people.
- 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716a5af0819095ea419a4d1f0d1d |
completed | April 20, 2026, 6:33 p.m. |
| PD | Predicate disambiguation | batch_69e55b18609481909ab28bc8750a642f |
completed | April 19, 2026, 10:45 p.m. |
Created at: April 11, 2026, 11:40 p.m.