Triple
T20708163
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hovedbanen company |
E508958
|
entity |
| Predicate | railwayStatusOfProject |
P139389
|
FINISHED |
| Object | public railway |
—
|
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: public railway | Statement: [Hovedbanen company, railwayStatusOfProject, public railway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: railwayStatusOfProject Context triple: [Hovedbanen company, railwayStatusOfProject, public railway]
-
A.
railStatus
Indicates the current operational condition or state of a rail-related entity (such as a track, line, or service) within the system.
-
B.
hasRailwayLineUnderConstruction
Indicates that a railway line associated with an entity is currently in the process of being built but not yet completed.
-
C.
railNetworkPhase
chosen
Indicates the specific stage or phase of development, implementation, or operation that a rail network is currently in.
-
D.
notableRailwayProject
Indicates that the subject is recognized for involvement in a significant or prominent railway-related project.
-
E.
railwayLineNow
Indicates that a previously existing railway line has been replaced, succeeded, or is currently represented by a new or different railway 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_69e0b4c40ad88190b81f77695366d328 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c1952e888190877b79933970f7b0 |
completed | April 21, 2026, 12:15 a.m. |
| PD | Predicate disambiguation | batch_69e5c044d1108190b2b5d25de23f6401 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:14 p.m.