Triple
T84890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flemish Americans |
E1707
|
entity |
| Predicate | heritageLanguageShift |
P4295
|
FINISHED |
| Object | from Dutch to English over generations |
—
|
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: from Dutch to English over generations | Statement: [Flemish Americans, heritageLanguageShift, from Dutch to English over generations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heritageLanguageShift Context triple: [Flemish Americans, heritageLanguageShift, from Dutch to English over generations]
-
A.
languageFamily
Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
-
B.
historicallySpokenIn
Indicates that a language was used for spoken communication in a particular place or region during a past historical period.
-
C.
nativeLanguage
Indicates the language that a person or entity originally learned and uses as their primary or first language.
-
D.
languageBranch
Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
-
E.
hasLanguageOfOrigin
Indicates that one entity has its origin or source in the language specified by another entity.
- 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_69a24c8150408190910a693eb51c1f71 |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a250e401288190ba12322c9c5f07c9 |
completed | Feb. 28, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69a24eb59e808190811c20518f39b1cc |
completed | Feb. 28, 2026, 2:11 a.m. |
| PDg | Predicate description generation | batch_69a250e2a80881909e5a653260e6f8e0 |
completed | Feb. 28, 2026, 2:20 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.