Triple
T21517089
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Walrus-class submarine |
E530871
|
entity |
| Predicate | successorClassPlanned |
P10131
|
FINISHED |
| Object | Walrus-class replacement program |
—
|
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: Walrus-class replacement program | Statement: [Walrus-class submarine, successorClassPlanned, Walrus-class replacement program]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorClassPlanned Context triple: [Walrus-class submarine, successorClassPlanned, Walrus-class replacement program]
-
A.
successorClass
chosen
Indicates that one class directly follows or replaces another class in a sequence or hierarchy.
-
B.
successorPlannedName
Indicates that a new name has been planned to replace or succeed the current name.
-
C.
successorProject
Indicates that one project directly follows and continues or replaces another project in sequence.
-
D.
successorType
Indicates the specific kind or category of successor relationship that holds between one entity and the next in a sequence or hierarchy.
-
E.
successorModel
Indicates that one model is the direct follow-up or replacement for another earlier model.
- 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_69e0c45d95a081908e7962ad215da746 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee814278e08190a66d516bed0726b5 |
completed | April 26, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:25 p.m.