Triple
T9048624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ANA Mileage Club |
E216823
|
entity |
| Predicate | supportsFamilyPooling |
P45052
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [ANA Mileage Club, supportsFamilyPooling, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsFamilyPooling Context triple: [ANA Mileage Club, supportsFamilyPooling, true]
-
A.
allowsFamilyPooling
chosen
Indicates that one entity permits multiple related individuals to combine or share their resources, benefits, or access as a family unit.
-
B.
usesPooling
Indicates that one entity employs a pooling mechanism or strategy to aggregate or combine resources, data, or elements from multiple sources.
-
C.
hasPool
Indicates that one entity possesses, includes, or is equipped with a swimming pool.
-
D.
hasPoolType
Indicates that an entity’s swimming pool possesses a specific type or classification (e.g., indoor, outdoor, heated).
-
E.
usesPoolingFilterSize
Indicates that an entity applies a pooling operation with a specified filter (kernel) size in a computational or neural network context.
- 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_69ca83d362e88190ae44b4e4dc194209 |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b51aa708190a37feecfd8deed2f |
completed | April 1, 2026, 12:48 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee566b081909e3cdaf551dbd0ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:09 p.m.