Triple
T5342003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ula-class submarine |
E123964
|
entity |
| Predicate | sonarSuite |
P63129
|
FINISHED |
| Object | bow-mounted sonar |
—
|
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: bow-mounted sonar | Statement: [Ula-class submarine, sonarSuite, bow-mounted sonar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sonarSuite Context triple: [Ula-class submarine, sonarSuite, bow-mounted sonar]
-
A.
usesPMD
Indicates that one entity employs or applies PMD (a specific tool, method, or metric) in relation to another entity or context.
-
B.
codeSpace
Indicates the namespace or contextual scope within which a piece of code, identifier, or programming element is defined and interpreted.
-
C.
oversightTools
Indicates that certain tools or mechanisms are used to monitor, review, or supervise the actions or performance of an entity.
-
D.
lighthouseAutomated
Indicates that a lighthouse operates automatically without the need for on-site human keepers.
-
E.
testedFor
Indicates that an entity has been examined or analyzed to determine the presence, absence, or level of another specified entity or condition.
- 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_69bd464b07f8819095aa76577c9829e4 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd85e86edc81908d87933db6489f91 |
completed | March 20, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69bd845a62b081909782863865b257a9 |
completed | March 20, 2026, 5:31 p.m. |
| PDg | Predicate description generation | batch_69bd85e69e808190b29548670fd2900a |
completed | March 20, 2026, 5:37 p.m. |
Created at: March 20, 2026, 2 p.m.