Triple
T15841786
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gotland-class submarine |
E384117
|
entity |
| Predicate | canLaunchWeapon |
P17728
|
FINISHED |
| Object | heavyweight torpedoes |
—
|
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: heavyweight torpedoes | Statement: [Gotland-class submarine, canLaunchWeapon, heavyweight torpedoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: canLaunchWeapon Context triple: [Gotland-class submarine, canLaunchWeapon, heavyweight torpedoes]
-
A.
canBeArmed
Indicates that an entity has the capability or option to be equipped with weapons or armaments.
-
B.
weaponControl
Indicates that one entity has authority over, access to, or the ability to direct the use of a weapon associated with another entity.
-
C.
usedWeapon
Indicates that an entity employed a specific weapon as the means or tool to carry out an action or event.
-
D.
supportsWeapon
chosen
Indicates that one entity is capable of accommodating, using, or being compatible with a specified weapon.
-
E.
hasWeaponType
Indicates that an entity is associated with or equipped with a specific type or category of weapon.
- 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_69d86da34c888190976e06c4019d415a |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e142e764088190afba6c5c1acf8199 |
completed | April 16, 2026, 8:13 p.m. |
| PD | Predicate disambiguation | batch_69e005434ed88190baf11c169da3cf29 |
completed | April 15, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:50 a.m.