Triple
T19116906
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T'way Air |
E467929
|
entity |
| Predicate | brandName |
P1500
|
FINISHED |
| Object | T'way Air |
—
|
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: T'way Air | Statement: [T'way Air, brandName, T'way Air]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T'way Air Context triple: [T'way Air, brandName, T'way Air]
-
A.
T'way Air
chosen
T'way Air is a South Korean low-cost airline headquartered in Seoul that operates domestic and international flights across Asia.
-
B.
Tigerair Taiwan
Tigerair Taiwan is a Taiwanese low-cost airline based in Taoyuan that operates regional flights across East and Southeast Asia.
-
C.
Loong Air
Loong Air is a Chinese passenger and cargo airline based in Hangzhou that operates domestic and regional routes across Asia.
-
D.
EVA Air
EVA Air is a major Taiwanese international airline known for its extensive global route network, high service standards, and innovative themed flights such as its Hello Kitty jets.
-
E.
Dragonair
Dragonair was a Hong Kong-based regional airline, later rebranded as Cathay Dragon, that primarily operated flights within Asia.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e399a6d8819090a9501ff1637b9d |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:05 p.m.