Triple
T10708269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nevsky Prospekt |
E252466
|
entity |
| Predicate | transferToLineNumber |
P42836
|
FINISHED |
| Object | Line 3 |
—
|
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: Line 3 | Statement: [Nevsky Prospekt, transferToLineNumber, Line 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: transferToLineNumber Context triple: [Nevsky Prospekt, transferToLineNumber, Line 3]
-
A.
throughServiceToLine
Indicates that a service operates through or along a specified line, establishing a through-service relationship between the service and the line.
-
B.
transferDestination
Indicates the entity that serves as the receiving end or target location of a transfer from another entity.
-
C.
transferLine
Indicates a relationship where something is moved or conveyed from one point, medium, or entity to another along a defined path or channel.
-
D.
interchangeWithLine
chosen
Indicates that one entity can be transferred or switched to another specific line, such as a route, track, or service line, at a given point.
-
E.
trimPositionIn88Line
Indicates the position or location where trimming occurs within an 88-character (or 88-unit) line.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fe5063bc8190ba12fd68a59c9a03 |
completed | April 9, 2026, 1:18 a.m. |
| PD | Predicate disambiguation | batch_69d6f30455888190b77f476b8418eaee |
completed | April 9, 2026, 12:29 a.m. |
Created at: April 8, 2026, 9:13 p.m.