Triple
T10109178
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kirov-class battlecruiser |
E218196
|
entity |
| Predicate | antiSubmarineWeapons |
P20717
|
FINISHED |
| Object | RBU rocket launchers |
—
|
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: RBU rocket launchers | Statement: [Kirov-class battlecruiser, antiSubmarineWeapons, RBU rocket launchers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: antiSubmarineWeapons Context triple: [Kirov-class battlecruiser, antiSubmarineWeapons, RBU rocket launchers]
-
A.
antiSubmarineArmament
chosen
Indicates the type or presence of weapons or equipment specifically designed for anti-submarine warfare associated with an entity.
-
B.
armamentTorpedoes
Indicates that an entity is equipped with torpedoes as part of its armament or weaponry.
-
C.
engagedSubmarines
Indicates that one entity took hostile or combat action against submarines belonging to another entity.
-
D.
antiTorpedoProtection
Indicates a defensive relationship where measures are in place to protect against or mitigate the effects of torpedo attacks.
-
E.
armamentCategory
Indicates the classification of a weapon or military equipment according to its type or role in armament systems.
- 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_69ca83da93fc8190b54e44bc2b34857c |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd0cbd8a48190b2af6177d1249f58 |
completed | April 2, 2026, 2:13 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9ed7e48190aa132ef8a69b49f9 |
completed | April 1, 2026, 4:45 p.m. |
Created at: March 30, 2026, 9:03 p.m.