Triple
T33842121
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dhuwa and Yirritja |
E867384
|
entity |
| Predicate | divide |
P889
|
FINISHED |
| Object | Yolngu society |
—
|
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: Yolngu society | Statement: [Dhuwa and Yirritja, divide, Yolngu society]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: divide Context triple: [Dhuwa and Yirritja, divide, Yolngu society]
-
A.
division
chosen
Indicates a relationship where one entity is separated or partitioned into parts, groups, or sections based on some criterion or operation.
-
B.
divisionAssignment
Indicates that one entity is assigned to or associated with a particular division within an organizational or structural hierarchy.
-
C.
divisionRenamedFrom
Indicates that a division currently known by one name was previously known by another specified name.
-
D.
divisionSince
Indicates that one entity has been divided or split from another starting at a specific point in time.
-
E.
divisionContext
Indicates the situational or conceptual setting in which a division operation or separation between entities takes place.
- 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_69f34992ad40819087760ed939bd2a7a |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69f7005069dc8190a8473c015571a4a0 |
completed | May 3, 2026, 7:59 a.m. |
| PD | Predicate disambiguation | batch_69f6fc59518081908b0275f47721d561 |
completed | May 3, 2026, 7:42 a.m. |
Created at: May 1, 2026, 1:47 a.m.