Triple
T33842151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dhuwa and Yirritja |
E867384
|
entity |
| Predicate | helpMaintain |
P96744
|
FINISHED |
| Object | social balance |
—
|
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: social balance | Statement: [Dhuwa and Yirritja, helpMaintain, social balance]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpMaintain Context triple: [Dhuwa and Yirritja, helpMaintain, social balance]
-
A.
helpsSustain
chosen
Indicates that one entity contributes to maintaining, supporting, or prolonging the existence, condition, or operation of another.
-
B.
oftenMaintain
Indicates that one entity frequently performs the action of maintaining or keeping another entity in a particular state or condition.
-
C.
helpsIn
Indicates that one entity provides assistance, support, or aid to another entity in performing or achieving a particular task, activity, or goal.
-
D.
canMaintain
Indicates that one entity has the ability or capacity to maintain, service, or keep another entity in proper working condition.
-
E.
oftenMaintainedBy
Indicates that something is regularly or frequently kept in working order, cared for, or updated by a particular agent or entity.
- 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.