Triple
T17334340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | XP (Flying Blue) |
E420895
|
entity |
| Predicate | earningSource |
P127052
|
FINISHED |
| Object | eligible flights on Air France |
—
|
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: eligible flights on Air France | Statement: [XP (Flying Blue), earningSource, eligible flights on Air France]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earningSource Context triple: [XP (Flying Blue), earningSource, eligible flights on Air France]
-
A.
earningChannel
Indicates the means or channel through which income, revenue, or earnings are generated.
-
B.
teachableSource
Indicates that one entity serves as a source from which another can be taught or can learn.
-
C.
learn
Indicates that an entity acquires knowledge, skills, or understanding from another entity, source, or experience.
-
D.
educationalHubFor
Indicates that one entity serves as a central place or resource for providing education, learning opportunities, or academic support to another entity.
-
E.
learnsLanguageFrom
Indicates that one entity acquires or improves knowledge of a language through instruction, exposure, or guidance provided by another entity.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a106df48190a50f96febc13cde7 |
completed | April 19, 2026, 2:12 a.m. |
| PD | Predicate disambiguation | batch_69e3b021a5bc81909ae55406f9d0b37f |
completed | April 18, 2026, 4:24 p.m. |
| PDg | Predicate description generation | batch_69e3b2a225b08190a50f984caa6513b9 |
completed | April 18, 2026, 4:34 p.m. |
Created at: April 10, 2026, 5:43 a.m.