Triple
T33515769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Danube |
E858360
|
entity |
| Predicate | designedYieldOptions |
P43516
|
FINISHED |
| Object | variable yields around 10 kilotons |
—
|
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: variable yields around 10 kilotons | Statement: [Blue Danube, designedYieldOptions, variable yields around 10 kilotons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedYieldOptions Context triple: [Blue Danube, designedYieldOptions, variable yields around 10 kilotons]
-
A.
hasYield
Indicates that one entity produces, returns, or generates a measurable output, result, or profit for another entity or context.
-
B.
hasDesignOption
chosen
Indicates that an entity is associated with or offers a particular design alternative or configurable design choice.
-
C.
requiresLowerMaximumYields
Indicates that one entity imposes a constraint on another such that the allowed or achievable maximum yields must be reduced.
-
D.
yieldsViaVariation
Indicates that one entity produces or results in another through a process of variation or modification.
-
E.
yieldsEstimate
Indicates that one entity produces or provides an estimated value or outcome for another entity or situation.
- 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_69f3497721848190978fbee5e0a526f8 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe9dfaa2d08190b2084f63f842eb6b |
completed | May 9, 2026, 2:37 a.m. |
| PD | Predicate disambiguation | batch_69fe9bba947c81908b0b2b92a4d19b37 |
completed | May 9, 2026, 2:28 a.m. |
Created at: May 1, 2026, 1:39 a.m.