Triple
T9804650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embraer R-99 |
E237923
|
entity |
| Predicate | originPlatformRole |
P49775
|
FINISHED |
| Object | regional jet airliner |
—
|
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: regional jet airliner | Statement: [Embraer R-99, originPlatformRole, regional jet airliner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originPlatformRole Context triple: [Embraer R-99, originPlatformRole, regional jet airliner]
-
A.
originPlatform
Indicates the platform, system, or environment from which an entity, event, or piece of data originally comes.
-
B.
platformRole
chosen
Indicates the specific function, position, or level of responsibility an entity holds within a given platform or system.
-
C.
parentPlatformOwner
Indicates that one entity owns or has controlling ownership over the platform on which another (child) entity resides or operates.
-
D.
originalPlatformGeneration
Indicates that one platform is the initial or first-generation version from which another platform or subsequent generations are derived.
-
E.
consideredPlatform
Indicates that one entity is regarded or treated as a platform (e.g., a base, medium, or environment) for another entity or activity.
- 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_69ca84dd4608819097ff4ed00feca280 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdab7a0ce881908f0555d194dece3f |
completed | April 1, 2026, 11:34 p.m. |
| PD | Predicate disambiguation | batch_69cd03dd2da881909052fbf29736a773 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:29 p.m.