Triple
T1534809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UberX |
E32525
|
entity |
| Predicate | cancellationPolicy |
P9633
|
FINISHED |
| Object | subject to Uber’s standard cancellation fees |
—
|
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: subject to Uber’s standard cancellation fees | Statement: [UberX, cancellationPolicy, subject to Uber’s standard cancellation fees]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cancellationPolicy Context triple: [UberX, cancellationPolicy, subject to Uber’s standard cancellation fees]
-
A.
cancellation
Indicates that a previously planned or scheduled event, action, or agreement is being annulled, terminated, or rendered no longer valid.
-
B.
cancellationReason
Indicates the reason or cause for which a previously scheduled or planned action, event, or agreement was canceled.
-
C.
venuePolicy
Indicates the rules or guidelines that govern how activities or events may be conducted at a particular venue.
-
D.
refundPolicy
Indicates the terms and conditions under which payments are returned or compensated after a purchase or transaction.
-
E.
reservationPolicy
chosen
Indicates the rules or conditions governing how reservations are made, modified, or canceled between parties.
- 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_69a885ea86308190998f6bc14bb91f8e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a915f323bc8190aa757142c225e0ae |
completed | March 5, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_69a907b046448190be8ea4d7b20255f7 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.