Triple
T174823
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cuban Americans |
E3552
|
entity |
| Predicate | heritageLanguage |
P6149
|
FINISHED |
| Object | Cuban Spanish |
—
|
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 Spanish | Statement: [Cuban Americans, heritageLanguage, Cuban Spanish]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageLanguage Context triple: [Cuban Americans, heritageLanguage, Cuban Spanish]
-
A.
heritageLanguageShift
Indicates a change over time in which a community or individual moves away from using their ancestral or heritage language toward another dominant language.
-
B.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
C.
influencedLanguage
Indicates that one language has had an effect on the development, structure, or usage of another language.
-
D.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by another entity.
-
E.
hasHeritage
Indicates that an entity possesses or is associated with a particular cultural, ethnic, or ancestral background.
- F. None of above. chosen
Provenance (4 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_69a25374990081909766d30c79a18e0e |
completed | Feb. 28, 2026, 2:31 a.m. |
| NER | Named-entity recognition | batch_69a258e32da88190ad9485aecd0bf08f |
completed | Feb. 28, 2026, 2:54 a.m. |
| PD | Predicate disambiguation | batch_69a256689f908190afeb5ee82022a911 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a25737f9188190b9690dce98aed83a |
completed | Feb. 28, 2026, 2:47 a.m. |
Created at: Feb. 28, 2026, 2:39 a.m.