Triple
T346281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haitian Americans |
E6948
|
entity |
| Predicate | media |
P2198
|
FINISHED |
| Object | Haitian Creole-language radio in the United States |
—
|
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: Haitian Creole-language radio in the United States | Statement: [Haitian Americans, media, Haitian Creole-language radio in the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: media Context triple: [Haitian Americans, media, Haitian Creole-language radio in the United States]
-
A.
mediaMarket
chosen
Indicates a relationship where a media outlet or content provider serves, targets, or operates within a particular geographic or demographic market.
-
B.
mediaCoverage
Indicates that one entity reports on, documents, or broadcasts information about another entity through news or media channels.
-
C.
mediaStrategy
Indicates a relationship where an entity plans, coordinates, or manages how media channels and content are used to achieve specific communication or marketing goals.
-
D.
mediaType
Indicates the format or category of media associated with an entity, such as text, image, audio, or video.
-
E.
mediaOrigin
Indicates the original source or provenance from which a piece of media (such as an image, video, or audio) was derived or obtained.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eb0240e88190bc70784772f5fa30 |
completed | Feb. 28, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69a2e95451a4819090f4e4fb9b21a493 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.