Triple
T19700091
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arbalet parachute system |
E473067
|
entity |
| Predicate | intendedJumpType |
P136986
|
FINISHED |
| Object | static-line jumps |
—
|
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: static-line jumps | Statement: [Arbalet parachute system, intendedJumpType, static-line jumps]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedJumpType Context triple: [Arbalet parachute system, intendedJumpType, static-line jumps]
-
A.
hasJump
Indicates that an entity performs or is capable of performing a jumping action.
-
B.
intendedProgram
Indicates the academic or training program that an entity plans or expects to pursue, rather than one they are currently enrolled in or have completed.
-
C.
intendedEngineType
Indicates that an entity is designed or specified to use a particular type of engine.
-
D.
jumpLength
Indicates the distance covered by an entity in a single jump.
-
E.
intendedTargetContext
Indicates the context, situation, or setting that an action, message, or object is specifically designed or meant to be used in or directed toward.
- F. None of above. chosen
Provenance (4 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_69d8e515bef88190bc30781aea50537a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e642b4e01081908f857f219d5d7a24 |
completed | April 20, 2026, 3:13 p.m. |
| PD | Predicate disambiguation | batch_69e530438c60819082364c7be3eef6f0 |
completed | April 19, 2026, 7:42 p.m. |
| PDg | Predicate description generation | batch_69e532bbedf081908d801600e2af94a7 |
completed | April 19, 2026, 7:53 p.m. |
Created at: April 10, 2026, 1:46 p.m.