Triple
T37901470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Petersburg–Vyborg line |
E945423
|
entity |
| Predicate | hasEndpointCityCountry |
P26386
|
FINISHED |
| Object | Saint Petersburg, Russia |
—
|
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: Saint Petersburg, Russia | Statement: [Saint Petersburg–Vyborg line, hasEndpointCityCountry, Saint Petersburg, Russia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndpointCityCountry Context triple: [Saint Petersburg–Vyborg line, hasEndpointCityCountry, Saint Petersburg, Russia]
-
A.
hasEndpointCity
chosen
Indicates that a route, connection, or path terminates at a particular city as one of its endpoints.
-
B.
hasEndpointCountry
Indicates that an entity such as a route, connection, or infrastructure element terminates or has an endpoint located in a specified country.
-
C.
endPointCityCountry
Indicates that a specific city and country serve as the ending location for a given route, trip, or connection.
-
D.
hasEndpointAirport
Indicates that something, such as a route or flight, has a specific airport as one of its terminal endpoints.
-
E.
hasEndCities
Indicates that something, typically a route or connection, is associated with specific cities at its endpoints.
- 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_69f76ef20bb0819088b5b6ceecb0b8fc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fe5c1a502081909d4024e514309c8e |
completed | May 8, 2026, 9:56 p.m. |
| PD | Predicate disambiguation | batch_69fe5a9df21c819087153f5d0bcaa987 |
completed | May 8, 2026, 9:50 p.m. |
Created at: May 3, 2026, 4:20 p.m.