Triple
T15221169
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EELV program |
E363767
|
entity |
| Predicate | costReductionTarget |
P95224
|
FINISHED |
| Object | at least 25 percent compared to heritage systems |
—
|
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: at least 25 percent compared to heritage systems | Statement: [EELV program, costReductionTarget, at least 25 percent compared to heritage systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: costReductionTarget Context triple: [EELV program, costReductionTarget, at least 25 percent compared to heritage systems]
-
A.
reducedCostOf
Indicates that one entity represents a lowered or discounted cost associated with another entity, typically compared to a standard or original price.
-
B.
targetReduction
chosen
Indicates a relationship where one entity is intended or expected to decrease, diminish, or lessen another entity by a specified amount or proportion.
-
C.
errorReductionGoal
Indicates that an entity has a target or objective to decrease the number or rate of errors relative to a current or baseline level.
-
D.
budgetTarget
Indicates that a specific financial goal or spending limit has been set for a given entity, period, or activity.
-
E.
costImpact
Indicates the effect that one entity or action has on the cost associated with another entity or process.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00788b04881909dad9b346ce3b4a9 |
completed | April 15, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69deca8479188190b2e5d3bc708d7d07 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:12 a.m.