Triple
T25842339
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Attack-class submarine |
E650968
|
entity |
| Predicate | programCostEstimate |
P4259
|
FINISHED |
| Object | tens of billions of Australian dollars |
—
|
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: tens of billions of Australian dollars | Statement: [Attack-class submarine, programCostEstimate, tens of billions of Australian dollars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programCostEstimate Context triple: [Attack-class submarine, programCostEstimate, tens of billions of Australian dollars]
-
A.
programCost
Indicates the monetary or resource expenditure required to implement, run, or participate in a particular program.
-
B.
estimatedCost
chosen
Indicates the predicted or calculated monetary amount expected to be required for something, such as a project, item, or action.
-
C.
programCostType
Indicates the type or category of cost associated with a program.
-
D.
economicCost
Indicates the financial burden, expense, or resource expenditure associated with an action, event, or relationship between entities.
-
E.
projectCostContext
Indicates the contextual factors or conditions under which a project's cost is defined, calculated, or interpreted.
- 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_69e7ab38086081908f3a8e7e0c6efd83 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6023564c08190a719144479d6a1b2 |
completed | May 2, 2026, 1:55 p.m. |
| PD | Predicate disambiguation | batch_69f5f7fba5248190945acf1561280799 |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 22, 2026, 7:50 a.m.