Triple
T30992672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tartu–Valga railway |
E789708
|
entity |
| Predicate | formsConnectionTo |
P845
|
FINISHED |
| Object | Latvian rail network via Valga |
—
|
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: Latvian rail network via Valga | Statement: [Tartu–Valga railway, formsConnectionTo, Latvian rail network via Valga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formsConnectionTo Context triple: [Tartu–Valga railway, formsConnectionTo, Latvian rail network via Valga]
-
A.
connectsTo
chosen
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
B.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
C.
connectsWorks
Indicates a relationship where one work serves to link, bridge, or associate two or more other works.
-
D.
connectsDestinationType
Indicates that one entity serves as a connection or link specifically to a destination of a given type.
-
E.
plannedToBeConnectedTo
Indicates that one entity is intended or scheduled to be linked or joined with another entity in the future.
- 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_69f224c550b081909ddfceb0c3d03bdd |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: April 29, 2026, 8:56 p.m.