Triple
T24875191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madang Province |
E622547
|
entity |
| Predicate | hasLocalLanguageFamily |
P152256
|
FINISHED |
| Object | Trans–New Guinea 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: Trans–New Guinea languages | Statement: [Madang Province, hasLocalLanguageFamily, Trans–New Guinea languages]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalLanguageFamily Context triple: [Madang Province, hasLocalLanguageFamily, Trans–New Guinea languages]
-
A.
isInLanguageFamily
Indicates that a language belongs to, or is classified within, a particular language family based on shared linguistic ancestry or characteristics.
-
B.
usesLanguageFamily
Indicates that an entity communicates or operates using a language that belongs to a specified language family.
-
C.
languageFamilyPresence
chosen
Indicates that a particular language family is present or attested within a specified region, group, or context.
-
D.
hasPrimaryVernacularLanguageFamily
Indicates that an entity’s main vernacular language belongs to a specified language family.
-
E.
hasFamilyNameInLanguage
Indicates that an entity has a specific family name as expressed or written in a particular 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_69e2fac3fdbc81909c2ec49be5743cd9 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f497bc12b881908fe3386c66252bf6 |
completed | May 1, 2026, 12:08 p.m. |
| PD | Predicate disambiguation | batch_69f49366e8d08190adb4b71fe3a14683 |
completed | May 1, 2026, 11:49 a.m. |
Created at: April 18, 2026, 5:24 a.m.