Triple
T26734911
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sapsan high-speed trains |
E674082
|
entity |
| Predicate | ticketClassBranding |
P37972
|
FINISHED |
| Object | Sapsan First |
—
|
NE NERFINISHED |
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: Sapsan First | Statement: [Sapsan high-speed trains, ticketClassBranding, Sapsan First]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ticketClassBranding Context triple: [Sapsan high-speed trains, ticketClassBranding, Sapsan First]
-
A.
ticketBranding
Indicates that one entity defines or is associated with the branding or visual identity applied to a ticket-related entity.
-
B.
ticketingBrandAccepted
Indicates that a particular ticketing brand is recognized and accepted for use in a given context or system.
-
C.
ticketClass
chosen
Indicates the category or level of service assigned to a ticket within a ticketing or reservation system.
-
D.
ticketClassSystem
Indicates that an entity is classified within a particular ticketing or fare class system that defines categories or levels of tickets.
-
E.
ticketFormat
Indicates the specific structure, layout, or template in which a ticket is represented or issued.
- 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_69eecda57ab481909424e98f2835e7d8 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f64dbbaefc8190952b8320bf4397d8 |
completed | May 2, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69f64cacd2c08190aed8a1761d0da679 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 3:46 a.m.