Triple
T2595345
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hiri Motu |
E58215
|
entity |
| Predicate | grammarType |
P4412
|
FINISHED |
| Object | SOV-dominant word order (with variation) |
—
|
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: SOV-dominant word order (with variation) | Statement: [Hiri Motu, grammarType, SOV-dominant word order (with variation)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: grammarType Context triple: [Hiri Motu, grammarType, SOV-dominant word order (with variation)]
-
A.
grammaticalType
Indicates the grammatical category or role (such as part of speech or syntactic function) that an expression has within a language.
-
B.
linguisticType
Indicates the type or category of language or linguistic system associated with an entity (e.g., spoken, signed, written, or other linguistic modality).
-
C.
tokenizerType
Indicates the specific tokenization method or algorithm used to split text into tokens.
-
D.
hasGrammar
Indicates that an entity possesses, follows, or is associated with a particular system of grammatical rules or structure.
-
E.
grammaticalStructure
chosen
Indicates the way linguistic elements are organized and related within a sentence or phrase according to grammatical rules.
- 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_69ab4ac14040819098b13f4a27d5c8ff |
completed | March 6, 2026, 9:44 p.m. |
| NER | Named-entity recognition | batch_69abd42978f881909f217e7ec9ac3144 |
completed | March 7, 2026, 7:30 a.m. |
| PD | Predicate disambiguation | batch_69abd0d344988190a18dd93b13e002e6 |
completed | March 7, 2026, 7:16 a.m. |
Created at: March 6, 2026, 9:49 p.m.