Triple
T29589554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TER Haute-Normandie |
E754114
|
entity |
| Predicate | partOfRailSystem |
P155710
|
FINISHED |
| Object | French national rail network |
—
|
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: French national rail network | Statement: [TER Haute-Normandie, partOfRailSystem, French national rail network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfRailSystem Context triple: [TER Haute-Normandie, partOfRailSystem, French national rail network]
-
A.
railwaySystemPartOf
chosen
Indicates that one railway-related component or subsystem belongs to, is included within, or forms a constituent part of a larger railway system.
-
B.
partOfTransitSystem
Indicates that something is a component or segment within a larger transit or transportation system.
-
C.
railComponent
Indicates a relationship where one entity is a structural or functional part of a rail or railway system component of another entity.
-
D.
partOfRailwayCorridor
Indicates that one entity is a segment, component, or area belonging to or contained within a specific railway corridor.
-
E.
connectsToRailStation
Indicates that one entity has a direct link, route, or access connection to a rail station.
- 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_69f0ef836ac88190bd809dc58b5ec907 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69feb8e856d48190aa34ad8ee8376e1c |
completed | May 9, 2026, 4:32 a.m. |
| PD | Predicate disambiguation | batch_69feb82a2b6c8190a473cc25976897be |
completed | May 9, 2026, 4:29 a.m. |
Created at: April 28, 2026, 6:13 p.m.