Triple
T38272172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Air Koryo |
E1021242
|
entity |
| Predicate | serviceQualityReputation |
P195335
|
FINISHED |
| Object | low service quality reputation |
—
|
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: low service quality reputation | Statement: [Air Koryo, serviceQualityReputation, low service quality reputation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceQualityReputation Context triple: [Air Koryo, serviceQualityReputation, low service quality reputation]
-
A.
performanceReputation
Indicates the perceived quality or reliability of an entity’s past or expected performance as judged by others.
-
B.
durabilityReputation
Indicates the perceived reliability and longevity of an entity’s products or services based on past performance or user experience.
-
C.
editorialReputation
Indicates the perceived quality, reliability, and integrity of an entity’s editorial practices or content.
-
D.
venueReputation
Indicates the perceived quality or standing of a venue based on opinions, experiences, or evaluations associated with it.
-
E.
managerReputation
Indicates the perceived quality, trustworthiness, and effectiveness of a manager as judged by others.
- 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_69f76dee198c8190bf5109421e47a658 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fdbaa226708190b8ed96e93aad38de |
completed | May 8, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69fdb58b07e48190837e00966de050d4 |
completed | May 8, 2026, 10:06 a.m. |
| PDg | Predicate description generation | batch_69fdbaa1313081908beea28a5597ae40 |
completed | May 8, 2026, 10:27 a.m. |
Created at: May 3, 2026, 4:30 p.m.