Triple
T26672557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mala Rijeka Viaduct |
E672372
|
entity |
| Predicate | carriedLine |
P51670
|
FINISHED |
| Object | Belgrade–Bar railway |
—
|
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: Belgrade–Bar railway | Statement: [Mala Rijeka Viaduct, carriedLine, Belgrade–Bar railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carriedLine Context triple: [Mala Rijeka Viaduct, carriedLine, Belgrade–Bar railway]
-
A.
carriedByLine
chosen
Indicates that something (such as a service, signal, or connection) is transported or conveyed via a particular line or conduit.
-
B.
carriedFor
Indicates that one entity transported or bore another entity on behalf of or for the benefit of that other entity.
-
C.
carriedTo
Indicates that one entity transported or conveyed another entity from one place to another.
-
D.
followedLineOf
Indicates that one entity moved along or traced the same path or trajectory previously taken or defined by another entity.
-
E.
formedLine
Indicates that an entity has arranged itself or others into a line or linear formation.
- 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_69eecda00a9c8190b2691f4d89db03b6 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69f63fd6c68481908c542aa03e297b9c |
completed | May 2, 2026, 6:17 p.m. |
| PD | Predicate disambiguation | batch_69f63c663be481908f233d25d28713a4 |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 3:13 a.m.