Triple
T7970976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FastPass+ |
E185320
|
entity |
| Predicate | queueBenefit |
P79751
|
FINISHED |
| Object | reduced wait time compared to standby |
—
|
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: reduced wait time compared to standby | Statement: [FastPass+, queueBenefit, reduced wait time compared to standby]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: queueBenefit Context triple: [FastPass+, queueBenefit, reduced wait time compared to standby]
-
A.
queueType
Indicates the classification or category of a queue that specifies how items in it are organized, prioritized, or processed.
-
B.
queueLocation
Indicates the place or position where an entity is arranged to wait in a queue or line.
-
C.
benefitAvailableAt
chosen
Indicates that a particular benefit can be obtained, accessed, or used at a specified location, time, or context.
-
D.
queueLength
Indicates the current number of items or entities waiting in a queue.
-
E.
isNextInLineTo
Indicates that one entity is immediately scheduled or positioned to receive something or assume a role after another entity.
- 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_69ca8297699481909b75a405f01e03af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bd304dc8190b9feee5e17fc66db |
completed | March 31, 2026, 3:13 a.m. |
| PD | Predicate disambiguation | batch_69cb047a8e4c81909b79e0f0bf56440c |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:13 p.m.