Triple
T30979748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corporate Airlines |
E789330
|
entity |
| Predicate | operatedUnderMarketingBrand |
P27763
|
FINISHED |
| Object | AmericanConnection |
—
|
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: AmericanConnection | Statement: [Corporate Airlines, operatedUnderMarketingBrand, AmericanConnection]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatedUnderMarketingBrand Context triple: [Corporate Airlines, operatedUnderMarketingBrand, AmericanConnection]
-
A.
operatedByBrand
Indicates that an entity (such as a service, location, or product line) is run, managed, or controlled by a particular brand.
-
B.
laterBrandOf
Indicates that one brand is a subsequent or successor brand to another, coming into use at a later time.
-
C.
operatedChannelBrand
Indicates that a brand is responsible for operating or managing a particular channel.
-
D.
hasUnderlyingCompanyBrand
chosen
Indicates that one entity is associated with or operates under the corporate brand of another company as its underlying brand.
-
E.
introducedUnderBrand
Indicates that one entity was launched, released, or brought to market using the branding or brand identity of another entity.
- 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_69f224c4831c8190be53924ec25a150a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69ff8aff48988190a48a440de8238ef9 |
completed | May 9, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69ff8a780404819082f48ceb21e7fe11 |
completed | May 9, 2026, 7:26 p.m. |
Created at: April 29, 2026, 8:55 p.m.