Triple
T37720423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crew Dragon In-Flight Abort Test |
E939567
|
entity |
| Predicate | abortMode |
P148356
|
FINISHED |
| Object | SuperDraco-powered launch escape |
—
|
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: SuperDraco-powered launch escape | Statement: [Crew Dragon In-Flight Abort Test, abortMode, SuperDraco-powered launch escape]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: abortMode Context triple: [Crew Dragon In-Flight Abort Test, abortMode, SuperDraco-powered launch escape]
-
A.
abortModeUsed
chosen
Indicates that an operation, process, or procedure was carried out using an abort or emergency-termination mode.
-
B.
abortSystemType
Indicates that a system or process is terminated or halted based on its specific type or classification.
-
C.
failureBehavior
Indicates how a system, component, or process is expected to respond or act when a failure or error condition occurs.
-
D.
escapeBehavior
Indicates a relationship where an entity actively attempts to avoid, flee from, or get away from another entity, situation, or constraint.
-
E.
launchFailureMode
Indicates the specific way in which a launch attempt fails or the type of failure that occurs during a launch.
- 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_69f76edc208c8190bc8b9683f75e1024 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbaef0cec881908c2742d77d145901 |
completed | May 6, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69fbadf632ec8190b14991c971258307 |
completed | May 6, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:18 p.m.