Triple
T6737366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States battleship fleet |
E153988
|
entity |
| Predicate | typicalProtection |
P15826
|
FINISHED |
| Object | thick belt armor |
—
|
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: thick belt armor | Statement: [United States battleship fleet, typicalProtection, thick belt armor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalProtection Context triple: [United States battleship fleet, typicalProtection, thick belt armor]
-
A.
typicalSecurityLevel
Indicates the usual or standard security level that is generally applied or expected in a given context or system.
-
B.
protectionType
chosen
Indicates the kind or method of protection that is applied to or associated with an entity.
-
C.
protectionCategory
Indicates a classification relationship where an entity is assigned to a specific type or level of protection based on defined protective criteria or rules.
-
D.
providesProtectionAgainst
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
-
E.
protectedBy
Indicates that one entity provides protection, defense, or safeguarding for another entity.
- 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_69c6880d84d8819095d19de2295f26ac |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1850a288190aa7e647fefbb0ede |
completed | March 27, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69c6d09067a0819087ed6c820f4699f8 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:10 p.m.