Triple
T25715487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FLYER |
E644850
|
entity |
| Predicate | usedByAirlineSubsidiaryOf |
P165317
|
FINISHED |
| Object | International Airlines Group |
—
|
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: International Airlines Group | Statement: [FLYER, usedByAirlineSubsidiaryOf, International Airlines Group]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedByAirlineSubsidiaryOf Context triple: [FLYER, usedByAirlineSubsidiaryOf, International Airlines Group]
-
A.
usedByAirlineAlsoKnownAs
Indicates that an item (such as a code, name, or identifier) is used by an airline that is also known by an alternative name.
-
B.
usedByAirlineIATA
Indicates that something (such as a code, resource, or facility) is utilized or operated by an airline identified by its IATA code.
-
C.
airlineParentCompany
Indicates that one company is the parent or owning company of an airline.
-
D.
hasSisterAirline
Indicates that one airline is related to another as its sister airline, typically sharing common ownership, management, or branding.
-
E.
usedByAirlineRole
Indicates that something (such as a resource, system, or process) is utilized by a specific role or position within an airline organization.
- F. None of above. chosen
Provenance (4 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_69e77e8476fc8190bd5e9d05b89fad0a |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f658a91ba0819084fbe3dd8a09f7cd |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f657f2c8b08190bfeb3173ef78207d |
completed | May 2, 2026, 8 p.m. |
Created at: April 21, 2026, 9:40 p.m.