Triple
T1543471
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Business Select |
E32922
|
entity |
| Predicate | refundMethod |
P9378
|
FINISHED |
| Object | original form of payment if canceled before departure |
—
|
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: original form of payment if canceled before departure | Statement: [Business Select, refundMethod, original form of payment if canceled before departure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refundMethod Context triple: [Business Select, refundMethod, original form of payment if canceled before departure]
-
A.
paymentMethod
Indicates the means or instrument through which a payment is made in a transaction.
-
B.
refundPolicy
Indicates the terms and conditions under which payments are returned or compensated after a purchase or transaction.
-
C.
disbursementOption
chosen
Indicates the method or arrangement by which funds are paid out or distributed.
-
D.
submissionMethod
Indicates the means or channel through which something is submitted or delivered.
-
E.
paymentSystem
Indicates a relationship where one entity functions as a mechanism or platform through which another entity makes or processes payments.
- 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_69a885ed29088190a3c2d5a3d100c16e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa95c1a2948190a2b98469afec1a7d |
completed | March 6, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_69a907b2453c8190a41f6b88c8217d1e |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.