Triple
T13090602
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tupolev Tu-91 |
E310450
|
entity |
| Predicate | designedForTask |
P9494
|
FINISHED |
| Object | ship attack |
—
|
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: ship attack | Statement: [Tupolev Tu-91, designedForTask, ship attack]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: designedForTask Context triple: [Tupolev Tu-91, designedForTask, ship attack]
-
A.
isDesignedFor
chosen
Indicates that one entity has been created, planned, or optimized specifically to serve the needs, purposes, or use of another entity.
-
B.
designedWith
Indicates that one entity was created, planned, or developed using another entity as a tool, method, or guiding basis in its design process.
-
C.
isDesignedAs
Indicates that something has been intentionally created or configured to serve as or function in the role of something else.
-
D.
appliesToDesignGoal
Indicates that something (such as a method, rule, or constraint) is relevant or intended to be used for achieving a particular design goal.
-
E.
designedFeature
Indicates that one entity is a feature or component intentionally planned, created, or specified by another entity as part of a design.
- 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_69d806a733548190989cfd4ce981ca33 |
completed | April 9, 2026, 8:05 p.m. |
| NER | Named-entity recognition | batch_69d98138a1d481908a139f2f67eb3472 |
completed | April 10, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69d9803f6c508190bfadfbc2d00c2c64 |
completed | April 10, 2026, 10:57 p.m. |
Created at: April 9, 2026, 9:03 p.m.