Triple
T15841769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gotland-class submarine |
E384117
|
entity |
| Predicate | AIPTechnology |
P120065
|
FINISHED |
| Object | Stirling engine |
—
|
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: Stirling engine | Statement: [Gotland-class submarine, AIPTechnology, Stirling engine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: AIPTechnology Context triple: [Gotland-class submarine, AIPTechnology, Stirling engine]
-
A.
AIPType
Indicates that an entity is classified by a specific AIP (Artificial Intelligence Program/Protocol) type or category.
-
B.
hasAI
Indicates that one entity possesses, incorporates, or is equipped with an artificial intelligence system.
-
C.
usesNeuralNetworks
Indicates that one entity employs neural network models or techniques as part of its functioning, processing, or decision-making.
-
D.
integratesNeuralEngine
Indicates that one entity incorporates or embeds a neural processing engine within its overall system or architecture.
-
E.
isStateOfTheArt
Indicates that something represents the most advanced, up-to-date, or cutting-edge level of development or performance in its field.
- 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_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. |
| PDg | Predicate description generation | batch_69e007869ae481909473ee220a7ccdb5 |
completed | April 15, 2026, 9:47 p.m. |
Created at: April 10, 2026, 4:50 a.m.