Triple
T32265706
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Select American Express Corporate Cards |
E824276
|
entity |
| Predicate | travelBenefit |
P175824
|
FINISHED |
| Object | trip delay coverage |
—
|
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: trip delay coverage | Statement: [Select American Express Corporate Cards, travelBenefit, trip delay coverage]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: travelBenefit Context triple: [Select American Express Corporate Cards, travelBenefit, trip delay coverage]
-
A.
travelAllowance
Indicates that an entity is entitled to or receives a monetary allowance specifically for travel-related expenses.
-
B.
airportBenefit
Indicates that one entity gains an advantage, profit, or positive impact from the existence, operation, or services of an airport.
-
C.
travelMechanic
Indicates the method or system by which movement or travel between locations is carried out.
-
D.
travelRuling
Indicates a legal or authoritative decision that determines whether, how, or under what conditions travel may occur.
-
E.
coTraveler
Indicates that two or more entities are traveling together along (part of) the same journey or route.
- F. None of above. chosen
Provenance (4 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_69f3490e73588190915f282edd105772 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6d74b20a48190900dda1014cc13a8 |
completed | May 3, 2026, 5:04 a.m. |
| PD | Predicate disambiguation | batch_69f6d26f27dc8190ae426a3e1573933e |
completed | May 3, 2026, 4:43 a.m. |
| PDg | Predicate description generation | batch_69f6d749e7f081909c8196898c4191ad |
completed | May 3, 2026, 5:04 a.m. |
Created at: May 1, 2026, 12:42 a.m.