Triple
T3688232
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Северо-Западный федеральный округ |
E78276
|
entity |
| Predicate | крупный порт |
P43437
|
FINISHED |
| Object | порт Санкт-Петербург |
—
|
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: порт Санкт-Петербург | Statement: [Северо-Западный федеральный округ, крупный порт, порт Санкт-Петербург]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: крупный порт Context triple: [Северо-Западный федеральный округ, крупный порт, порт Санкт-Петербург]
-
A.
isAmongLargestPortsIn
chosen
Indicates that a port ranks among the largest ports within a specified geographic or administrative area.
-
B.
majorPortCity
Indicates that a city functions as a primary maritime port, serving as a major hub for sea transport, trade, or shipping activities.
-
C.
porte
Indicates that an entity carries, wears, or bears another entity (such as an object, attribute, or characteristic).
-
D.
isLargestSeaportOn
Indicates that a seaport is the largest seaport located on a specified geographic feature, such as a coast, island, or body of water.
-
E.
isBusiestSeaportIn
Indicates that a seaport handles the highest volume of traffic or activity compared to all other seaports within a specified region or area.
- 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_69ad85e285a081908f8cbfa9e2ed9b75 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc4c960788190b73ede08658846aa |
completed | March 8, 2026, 6:49 p.m. |
| PD | Predicate disambiguation | batch_69adb84be1fc81909721c871babb4633 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:26 p.m.