Triple
T7446622
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samoa Islands archipelago |
E171898
|
entity |
| Predicate | demographicLanguageFamily |
P11493
|
FINISHED |
| Object | Austronesian languages |
—
|
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: Austronesian languages | Statement: [Samoa Islands archipelago, demographicLanguageFamily, Austronesian languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: demographicLanguageFamily Context triple: [Samoa Islands archipelago, demographicLanguageFamily, Austronesian languages]
-
A.
majorLanguageFamilies
Indicates that one entity is a primary or dominant language family to which the other entity (a language or group of languages) belongs.
-
B.
languageFamily
Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
-
C.
languageFamilyDominant
chosen
Indicates that one language family holds a primary or prevailing status over others within a given context (such as a region, population, or system).
-
D.
languageOfFamily
Indicates the language or languages commonly used or associated with a particular family.
-
E.
languageFamilyOf
Indicates that one entity is the language family to which the other entity (a specific language) belongs.
- 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_69c68a65402881908f7869368eb746fb |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f371be2081908feaeb9392cb65fe |
completed | March 27, 2026, 9:15 p.m. |
| PD | Predicate disambiguation | batch_69c6f039f7248190bb4183f97b605763 |
completed | March 27, 2026, 9:01 p.m. |
Created at: March 27, 2026, 3:14 p.m.