Triple
T31482653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Loyalty Islands |
E803188
|
entity |
| Predicate | localLanguageFamily |
P71895
|
FINISHED |
| Object | Austronesian languages |
—
|
NE NERFINISHED |
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: [Loyalty Islands, localLanguageFamily, Austronesian languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: localLanguageFamily Context triple: [Loyalty Islands, localLanguageFamily, Austronesian languages]
-
A.
nativeLanguageFamilyName
Indicates the name of the language family to which an entity’s native language belongs.
-
B.
primaryLocalLanguageFamily
chosen
Indicates the main linguistic family to which the predominant local language of an entity belongs.
-
C.
localLanguageName
Indicates the name of a language as it is written or referred to in its own local or native form.
-
D.
languageFamilyUsedFor
Indicates that a particular language family is employed or utilized for a specific purpose, context, or function.
-
E.
languageFamilyRegion
Indicates the geographic region or area in which a language family is predominantly found or historically associated.
- 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_69f348c9477c8190bc0a21f6d482d2fc |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6c1bb5f248190834161b5a6ba1ece |
completed | May 3, 2026, 3:32 a.m. |
| PD | Predicate disambiguation | batch_69f6bd25bed08190befcabd3a41ffadf |
completed | May 3, 2026, 3:12 a.m. |
Created at: April 30, 2026, 9:33 p.m.