Triple
T26170480
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berserker |
E654385
|
entity |
| Predicate | hasMainTechnology |
P133726
|
FINISHED |
| Object | self-replicating autonomous warships |
—
|
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: self-replicating autonomous warships | Statement: [Berserker, hasMainTechnology, self-replicating autonomous warships]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainTechnology Context triple: [Berserker, hasMainTechnology, self-replicating autonomous warships]
-
A.
isKeyTechnologyIn
Indicates that one technology plays a central, enabling, or foundational role within another specified context, system, or domain.
-
B.
hasTechnologyDomain
Indicates that an entity is associated with, operates within, or is relevant to a particular field or domain of technology.
-
C.
hasTechnologyTheme
Indicates that something is associated with, centers on, or prominently features technology as a primary theme or subject.
-
D.
hasTechnologicalActivity
Indicates that an entity engages in, performs, or is involved in some form of technological process, operation, or practice.
-
E.
hasTechnologySystem
chosen
Indicates that one entity possesses, utilizes, or is supported by a particular technology system.
- 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_69ee5b44391c81908bdbd8813ba9aa99 |
completed | April 26, 2026, 6:36 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 26, 2026, 8:35 p.m.