Triple
T29401811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | JPDA Treaty |
E745662
|
entity |
| Predicate | allocatesRevenueShareToAustralia |
P123642
|
FINISHED |
| Object | 10 percent |
—
|
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: 10 percent | Statement: [JPDA Treaty, allocatesRevenueShareToAustralia, 10 percent]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allocatesRevenueShareToAustralia Context triple: [JPDA Treaty, allocatesRevenueShareToAustralia, 10 percent]
-
A.
allocatesToCountry
Indicates that a resource, amount, or responsibility is assigned or distributed to a specific country.
-
B.
oilRevenueSharingRatio
chosen
Indicates the proportion in which oil-generated revenue is divided or shared between involved parties.
-
C.
AustraliaOvers
Indicates a relationship where one entity surpasses, exceeds, or goes beyond another in the specific context associated with Australia.
-
D.
australiaSupports
Indicates that Australia provides assistance, endorsement, or backing to another entity or action.
-
E.
isInAustralia
Indicates that the subject is located within the geographical boundaries of Australia.
- 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_69f0a79eb7d081908c67197a5f347e68 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f66a0838f0819096163ecd875df6e3 |
completed | May 2, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69f6659b62fc8190b21555d0ba54db2d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 2:51 p.m.