Triple
T16061512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | China United Airlines |
E389623
|
entity |
| Predicate | foundedAsCivilCarrier |
P99948
|
FINISHED |
| Object | 2005 |
—
|
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: 2005 | Statement: [China United Airlines, foundedAsCivilCarrier, 2005]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundedAsCivilCarrier Context triple: [China United Airlines, foundedAsCivilCarrier, 2005]
-
A.
airlineFoundedAs
Indicates that one airline was originally established or created under a particular initial name, structure, or predecessor airline.
-
B.
underlyingCompanyFoundedAsAirline
Indicates that the underlying company was originally established as an airline.
-
C.
airlineFoundedAsYear
chosen
Indicates the year in which an airline was originally founded under its initial identity or name.
-
D.
firstCommercialFlightDate
Indicates the calendar date on which an entity’s first commercial flight or revenue-earning air service took place.
-
E.
recommissionedAsCarrierYear
Indicates the year in which an entity was recommissioned specifically in the role or configuration of a carrier.
- 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_69d86dae698881908327ef2d67706cb9 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1858a00888190b8505071575dc56f |
completed | April 17, 2026, 12:57 a.m. |
| PD | Predicate disambiguation | batch_69e18272f2288190a17d45fb01cc2b07 |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 4:57 a.m.