Triple
T2092462
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Polynesian outliers |
E32700
|
entity |
| Predicate | hasSubgroupLanguageFamily |
P31853
|
FINISHED |
| Object | Polynesian 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: Polynesian languages | Statement: [Polynesian outliers, hasSubgroupLanguageFamily, Polynesian languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubgroupLanguageFamily Context triple: [Polynesian outliers, hasSubgroupLanguageFamily, Polynesian languages]
-
A.
hasSubLanguage
Indicates that one language is a subset, variant, or specialized form of another language.
-
B.
hasLanguageGroup
Indicates that an entity belongs to, is associated with, or is categorized under a particular language group.
-
C.
linguisticSubgroup
chosen
Indicates that one linguistic group forms a subordinate or specialized subset within a larger linguistic group or family.
-
D.
hasFamilyNameInLanguage
Indicates that an entity has a specific family name as expressed or written in a particular language.
-
E.
hasIndigenousLanguageFamily
Indicates that an entity’s indigenous language belongs to, or is classified under, a particular language family.
- 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_69a885eba0708190999696a45cbec816 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abba774ca881909f83cf65ffeb24bb |
completed | March 7, 2026, 5:41 a.m. |
| PD | Predicate disambiguation | batch_69abb7b6274081909df36cd7a7c6a675 |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:43 p.m.