Triple
T31970197
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spanker |
E816290
|
entity |
| Predicate | appliesToMissileClass |
P197521
|
FINISHED |
| Object | SS-17 |
—
|
NE NERFINISHED |
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: SS-17 | Statement: [Spanker, appliesToMissileClass, SS-17]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToMissileClass Context triple: [Spanker, appliesToMissileClass, SS-17]
-
A.
missileClass
Indicates the classification or type category assigned to a missile within a defined system or taxonomy.
-
B.
appliesToWeaponSystem
Indicates that something (such as a rule, configuration, or characteristic) is relevant or applicable to a particular weapon system.
-
C.
usesMissileSystem
Indicates that one entity employs or operates a particular missile system as part of its capabilities or actions.
-
D.
associatedWithMissile
Indicates a relationship in which an entity is connected or linked to a missile, such as through ownership, use, design, deployment, or operational involvement.
-
E.
compatibleMissile
Indicates that a missile can be correctly used with, mounted on, or launched by a given platform or launcher system.
- 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_69f348f5ae5481909da0247869f51955 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fe991bca608190b524e419642f4243 |
completed | May 9, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69fe979fc1c4819091fc48d63ea12063 |
completed | May 9, 2026, 2:10 a.m. |
| PDg | Predicate description generation | batch_69fe991abc6c81908edbb98d61c9ca73 |
completed | May 9, 2026, 2:16 a.m. |
Created at: May 1, 2026, 12:10 a.m.