Triple
T3782539
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OPUS card |
E85452
|
entity |
| Predicate | isContactless |
P15672
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [OPUS card, isContactless, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isContactless Context triple: [OPUS card, isContactless, true]
-
A.
supportsTapToPay
chosen
Indicates that an entity enables or is compatible with tap-to-pay (contactless) payment functionality.
-
B.
hasNFC
Indicates that one entity possesses or supports Near Field Communication (NFC) capability in relation to another entity or context.
-
C.
hasNearbyPass
Indicates that an entity has at least one pass (e.g., transit or access pass) available within a short or locally defined distance from it.
-
D.
cardAcceptance
Indicates that one party accepts or recognizes another party’s card as a valid form of payment or identification.
-
E.
supportsTapOnTapOff
Indicates that a system or service allows users to initiate and complete interactions or transactions by tapping a device or card at both the start and end of use.
- 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_69aed937fa8881908208ef3801060826 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aee634c6ac819099653c660c286746 |
completed | March 9, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69aee3d3c92c819081d9d5c45ef37a5d |
completed | March 9, 2026, 3:14 p.m. |
Created at: March 9, 2026, 3:13 p.m.