Triple
T10753387
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Miles&Smiles |
E253626
|
entity |
| Predicate | statusLevel |
P14125
|
FINISHED |
| Object | Elite Plus |
E882813
|
NE 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: Elite Plus | Statement: [Miles&Smiles, statusLevel, Elite Plus]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elite Plus Context triple: [Miles&Smiles, statusLevel, Elite Plus]
-
A.
Elite Plus
chosen
Elite Plus is the highest frequent-flyer status level in Turkish Airlines’ Miles&Smiles program, offering the most exclusive travel benefits and privileges.
-
B.
United Premium Plus
United Premium Plus is United Airlines’ premium economy cabin class that offers larger seats, enhanced amenities, and upgraded service compared with standard economy options.
-
C.
Elite
Elite is the top-tier luxury trim level of the Honda Odyssey minivan, featuring the most advanced comfort, technology, and safety amenities in the lineup.
-
D.
Elite
Elite is a Spanish teen drama thriller series on Netflix that follows the lives, secrets, and scandals of students at an exclusive private high school.
-
E.
Elite
Elite is a production company known for its work on the television series "Friday Night Lights."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6aa5e51e8819095f06881cecf152e |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d71dc2543c8190bb060aa7a1fed6a6 |
completed | April 9, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de2338b2cc8190ad40ff9a421a4152 |
completed | April 14, 2026, 11:21 a.m. |
Created at: April 8, 2026, 9:15 p.m.