Triple
T25782406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KC-45A |
E649324
|
entity |
| Predicate | programResult |
P13029
|
FINISHED |
| Object | lost re-compete to Boeing KC-46A |
—
|
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: lost re-compete to Boeing KC-46A | Statement: [KC-45A, programResult, lost re-compete to Boeing KC-46A]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programResult Context triple: [KC-45A, programResult, lost re-compete to Boeing KC-46A]
-
A.
programOutcome
chosen
Indicates the resulting state, effect, or consequence produced by executing or completing a program.
-
B.
programStatus
Indicates the current state or condition of a program within its lifecycle (e.g., planned, active, paused, completed, or terminated).
-
C.
producedProgram
Indicates that one entity created or produced a specific program (such as a TV show, software, or other structured content).
-
D.
program
Indicates that an entity creates, writes, or develops a computer program or software application.
-
E.
implementedProgram
Indicates that an entity has created, developed, or put into operation a particular program or software system.
- 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_69e7ab33e9308190afe415dc6f9e8876 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fe6175048190afd845628c74830e |
completed | May 2, 2026, 1:38 p.m. |
| PD | Predicate disambiguation | batch_69f5afec3e94819080d9ba86cf8c866e |
completed | May 2, 2026, 8:03 a.m. |
Created at: April 22, 2026, 5:51 a.m.