Triple
T13564627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tiwi language |
E324002
|
entity |
| Predicate | syntacticAlignment |
P76654
|
FINISHED |
| Object | nominative–accusative alignment |
—
|
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: nominative–accusative alignment | Statement: [Tiwi language, syntacticAlignment, nominative–accusative alignment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: syntacticAlignment Context triple: [Tiwi language, syntacticAlignment, nominative–accusative alignment]
-
A.
grammaticalAlignment
chosen
Indicates how a language aligns core grammatical roles (such as subject, object, or agent, patient) in its case marking or agreement system.
-
B.
alignmentRelation
Indicates that one entity is positioned, oriented, or arranged in a specific way relative to another entity.
-
C.
forceAlignment
Indicates that one entity compels another entity to match or conform its alignment, orientation, or position to its own or to a specified standard.
-
D.
eraAlignment
Indicates that two entities are associated with, or correspond to, the same historical or temporal era.
-
E.
syntacticType
Indicates the grammatical or structural category that characterizes how an expression functions within a syntactic construction.
- 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_69d8076830b48190910a902bae5888e2 |
completed | April 9, 2026, 8:09 p.m. |
| NER | Named-entity recognition | batch_69dbb00bbe848190bb33efe2af528295 |
completed | April 12, 2026, 2:45 p.m. |
| PD | Predicate disambiguation | batch_69dbae161a0481909f9d3f40ca4e0ac5 |
completed | April 12, 2026, 2:37 p.m. |
Created at: April 9, 2026, 9:47 p.m.