Triple
T37432607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Asiana Club miles |
E930181
|
entity |
| Predicate | trackedVia |
P154702
|
FINISHED |
| Object | Asiana Airlines website |
—
|
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: Asiana Airlines website | Statement: [Asiana Club miles, trackedVia, Asiana Airlines website]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trackedVia Context triple: [Asiana Club miles, trackedVia, Asiana Airlines website]
-
A.
trackedOn
chosen
Indicates that the subject’s status, activity, or changes are being monitored or recorded on the specified system, platform, or medium.
-
B.
trackingType
Indicates the method or category by which an entity’s movement, status, or progress is monitored or recorded.
-
C.
trackFrom
Indicates a source or origin from which something is tracked or monitored.
-
D.
traceOf
Indicates that one entity is a remaining sign, mark, or residual evidence of the presence, existence, or action of another entity.
-
E.
trackAccess
Indicates that one entity monitors, records, or keeps a log of another entity’s access or usage of a resource.
- 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_69f76ebfdcb8819098562ff3db673b04 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:17 p.m.