Triple
T33967798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BAC 223 |
E870901
|
entity |
| Predicate | developedForOperatorType |
P21524
|
FINISHED |
| Object | international airlines |
—
|
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: international airlines | Statement: [BAC 223, developedForOperatorType, international airlines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: developedForOperatorType Context triple: [BAC 223, developedForOperatorType, international airlines]
-
A.
developedForProduct
Indicates that something (such as a component, feature, or service) was specifically created or tailored to be used with or support a particular product.
-
B.
designedOperator
Indicates that an entity (typically a person or organization) intentionally created or planned the specified operator (such as a function, mechanism, or process) for a particular purpose.
-
C.
typicalOperatorType
chosen
Indicates the usual or most common type or category of operator associated with a given entity or context.
-
D.
developedForProgram
Indicates that something was created, designed, or produced specifically to be used in or support a particular program.
-
E.
developedForVendor
Indicates that something (such as a product, service, or solution) was specifically created or tailored to meet the needs or requirements of a particular vendor.
- 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_69f3499ce8e88190b66e1d49ad8c7037 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fcf36d2894819089b7db8e91b63c9d |
completed | May 7, 2026, 8:17 p.m. |
| PD | Predicate disambiguation | batch_69fcf25c0a108190bfa823474098640b |
completed | May 7, 2026, 8:13 p.m. |
Created at: May 1, 2026, 1:50 a.m.