Triple
T7317689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Karkar-Yuri languages |
E168454
|
entity |
| Predicate | neighboringLanguageArea |
P29819
|
FINISHED |
| Object | Madang languages area |
—
|
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: Madang languages area | Statement: [Karkar-Yuri languages, neighboringLanguageArea, Madang languages area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neighboringLanguageArea Context triple: [Karkar-Yuri languages, neighboringLanguageArea, Madang languages area]
-
A.
hasNeighboringLanguages
Indicates that two languages are geographically or regionally adjacent to each other in their areas of use.
-
B.
neighboringLanguageFamilies
Indicates that two language families are geographically adjacent or border each other in their primary regions of use.
-
C.
linguisticArea
Indicates a regional context in which languages share features due to geographic proximity and contact rather than common genetic origin.
-
D.
neighboringRegion
Indicates that two regions share a common boundary or are directly adjacent to each other geographically.
-
E.
languageArea
chosen
Indicates the geographic or cultural region in which a particular language is used or predominantly spoken.
- 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_69c68a5251508190ad68df4151cfeb04 |
completed | March 27, 2026, 1:46 p.m. |
| NER | Named-entity recognition | batch_69c6ef178b3081908cd0c62466069741 |
completed | March 27, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69c6e7705f4881909793071dee50c557 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 3:02 p.m.