Triple
T7918610
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patriot |
E183887
|
entity |
| Predicate | hasOriginPlatformRole |
P49775
|
FINISHED |
| Object | civilian transport helicopter |
—
|
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: civilian transport helicopter | Statement: [Patriot, hasOriginPlatformRole, civilian transport helicopter]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginPlatformRole Context triple: [Patriot, hasOriginPlatformRole, civilian transport helicopter]
-
A.
platformRole
chosen
Indicates the specific function, position, or level of responsibility an entity holds within a given platform or system.
-
B.
hasPlatformType
Indicates that an entity is associated with or characterized by a specific type or category of platform.
-
C.
hasPrimaryPlatform
Indicates that one entity is designated as the main or principal platform associated with another entity.
-
D.
hasLevelAccessToPlatforms
Indicates that an entity is permitted to access certain platforms at a specified level or tier of authorization.
-
E.
belongsToPlatform
Indicates that something is associated with, owned by, or part of a particular platform.
- 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_69ca828efbe48190bd48482650182e79 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a8fbbb48190b50def4941761a31 |
completed | March 31, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69cae9316e98819080be7bf1a6ff92f1 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:05 p.m.