Triple
T29448114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CSeries |
E746904
|
entity |
| Predicate | launchCustomerCS300 |
P13475
|
FINISHED |
| Object | airBaltic |
—
|
NE NERFINISHED |
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: airBaltic | Statement: [CSeries, launchCustomerCS300, airBaltic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: launchCustomerCS300 Context triple: [CSeries, launchCustomerCS300, airBaltic]
-
A.
launchCustomer
chosen
Indicates that an entity serves as an initial or flagship customer involved in the launch or early adoption of another entity’s product, service, or initiative.
-
B.
launchServiceCustomer
Indicates that a customer is the recipient or user of a launch service provided by another entity.
-
C.
exportCustomer
Indicates initiating the transfer or output of customer-related data from one system or context to another, typically for integration, backup, or reporting purposes.
-
D.
clientOf
Indicates that one entity receives services or conducts business from another entity in a client–provider relationship.
-
E.
programCustomer
Indicates that a customer is associated with or enrolled in a particular program.
- 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_69f0a7a230488190b44a97fe3d16f731 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f697eabb048190bc01a830f14942c6 |
completed | May 3, 2026, 12:33 a.m. |
| PD | Predicate disambiguation | batch_69f69664142c8190bc695501056b0236 |
completed | May 3, 2026, 12:27 a.m. |
Created at: April 28, 2026, 3:29 p.m.