Triple
T21938173
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lont |
E541747
|
entity |
| Predicate | scriptUsageLanguageFamily |
P143007
|
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: [Lont, scriptUsageLanguageFamily, Austronesian languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scriptUsageLanguageFamily Context triple: [Lont, scriptUsageLanguageFamily, Austronesian languages]
-
A.
languageFamilyUsedFor
Indicates that a particular language family is employed or utilized for a specific purpose, context, or function.
-
B.
usesLanguageFamily
Indicates that an entity communicates or operates using a language that belongs to a specified language family.
-
C.
languageFamily
Indicates that two or more languages belong to the same genealogical language family or linguistic lineage.
-
D.
languageFamilyDocumented
Indicates that there exists documentation or records describing the language family to which the entity’s language belongs.
-
E.
appliesToLanguageFamily
chosen
Indicates that something (such as a rule, feature, or classification) is relevant or applicable to an entire language family rather than to a single language.
- 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_69e0c47e2e5c81909a7f74ce3de50911 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1241e35bc81909eb3225d5cd97b92 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f5efc208819091ed2cf6841fa600 |
completed | April 21, 2026, 3:58 a.m. |
Created at: April 16, 2026, 7:55 p.m.