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.