Triple
T21772230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FJ Fury series |
E537461
|
entity |
| Predicate | launchRecoverySystem |
P43948
|
FINISHED |
| Object | catapult launch capable |
—
|
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: catapult launch capable | Statement: [FJ Fury series, launchRecoverySystem, catapult launch capable]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: launchRecoverySystem Context triple: [FJ Fury series, launchRecoverySystem, catapult launch capable]
-
A.
recoverySystem
Indicates a system or mechanism responsible for restoring a previous state, function, or data after a failure, loss, or disruption.
-
B.
launchAndRecovery
chosen
Indicates a relationship where one entity is responsible for both deploying (launching) another entity into operation and subsequently retrieving (recovering) it afterward.
-
C.
startingSystem
Indicates the system or context from which an action, process, or transition is initially begun.
-
D.
recoveryForce
Indicates the force exerted to restore an object or system from a displaced, deformed, or disturbed state back toward its original or equilibrium condition.
-
E.
recoveryMethod
Indicates the method or process by which something is restored, retrieved, or brought back to a previous or functional state.
- 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_69e0c470759c819094a215757113562b |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031af6a488190a2dcebed43d199d4 |
completed | April 28, 2026, 4:03 a.m. |
| PD | Predicate disambiguation | batch_69e6be6299988190a34c98fa76d94700 |
completed | April 21, 2026, 12:01 a.m. |
Created at: April 16, 2026, 6:51 p.m.