Triple
T25972811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Oneworld Ruby |
E645850
|
entity |
| Predicate | doesNotTypicallyInclude |
P131596
|
FINISHED |
| Object | lounge access |
—
|
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: lounge access | Statement: [Oneworld Ruby, doesNotTypicallyInclude, lounge access]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: doesNotTypicallyInclude Context triple: [Oneworld Ruby, doesNotTypicallyInclude, lounge access]
-
A.
doesNotCover
Indicates that one entity fails to include, protect, or extend over another entity or area.
-
B.
doesNotPrimarilyContain
Indicates that one entity does not have another entity as its main or predominant component, element, or content.
-
C.
doesNotProvideFor
chosen
Indicates that one entity fails or is not responsible for supplying support, resources, or necessary provisions to another entity.
-
D.
notTypicallyShownTo
Indicates that one entity is generally not displayed or presented to another entity under normal circumstances.
-
E.
doesNotGenerallyApplyTo
Indicates that a rule, property, or condition is typically not relevant or applicable to the referenced entity or situation in most cases.
- 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_69e77e8768648190b27bb578f14bcb88 |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f60c698ae48190871cd445422bad91 |
completed | May 2, 2026, 2:38 p.m. |
| PD | Predicate disambiguation | batch_69f60b874cc88190a487230abb69efea |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 22, 2026, 8:51 a.m.