Triple
T28569413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ukrainian Railways network |
E722773
|
entity |
| Predicate | isNationalNetwork |
P72739
|
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: [Ukrainian Railways network, isNationalNetwork, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isNationalNetwork Context triple: [Ukrainian Railways network, isNationalNetwork, true]
-
A.
connectedToNationalNetworkAt
Indicates that an entity has a direct linkage or access point to a broader national-level network or infrastructure.
-
B.
isPartOfNetworkServing
Indicates that one entity functions as a component within, or is supported by, a particular network that provides services to it or through it.
-
C.
isInCapitalCityNetwork
Indicates that an entity is part of a network connecting capital cities, typically through infrastructure, services, or administrative linkages.
-
D.
isNationwide
chosen
Indicates that something extends across or applies to an entire nation or country, rather than being limited to a specific region or locality.
-
E.
isIntegratedDeliveryNetwork
Indicates that a healthcare organization operates as an integrated delivery network, coordinating multiple care providers and services under unified management and systems.
- 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_69f01a5f69d08190ad5c0d2167078dec |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f6509183bc8190949afa859c96b649 |
completed | May 2, 2026, 7:29 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 4:09 a.m.