Triple
T6011852
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hunchback |
E133852
|
entity |
| Predicate | aircraftTorpedoArmament |
P13762
|
FINISHED |
| Object | up to two aerial 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: up to two aerial torpedoes | Statement: [Hunchback, aircraftTorpedoArmament, up to two aerial torpedoes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: aircraftTorpedoArmament Context triple: [Hunchback, aircraftTorpedoArmament, up to two aerial torpedoes]
-
A.
armamentTorpedoes
chosen
Indicates that an entity is equipped with torpedoes as part of its armament or weaponry.
-
B.
numberOfTorpedoTubes
Indicates the quantity of torpedo tubes associated with or installed on an entity.
-
C.
antiSubmarineArmament
Indicates the type or presence of weapons or equipment specifically designed for anti-submarine warfare associated with an entity.
-
D.
torpedoCaliber
Indicates the specific diameter or size classification of a torpedo used in a given context or system.
-
E.
referredAircraftArmament
Indicates that one aircraft’s armament is being referenced or pointed to in relation to another entity or context.
- 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_69c0087361a48190905c6b55969852b8 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f5159bc8190a988293bbbb99d24 |
completed | March 22, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69c049e4daf4819099bf870dc700e0a2 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:06 p.m.