Triple
T31841526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dijon–Langres railway |
E812821
|
entity |
| Predicate | locatedInCountryRailNetwork |
P186587
|
FINISHED |
| Object | SNCF network |
E93156
|
NE 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: SNCF network | Statement: [Dijon–Langres railway, locatedInCountryRailNetwork, SNCF network]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInCountryRailNetwork Context triple: [Dijon–Langres railway, locatedInCountryRailNetwork, SNCF network]
-
A.
railNetworkCountry
chosen
Indicates that a rail network is located within, or primarily serves, a specific country.
-
B.
isNationalRailwaySystemOf
Indicates that one entity functions as the official national railway system serving and operating within the territory of another entity.
-
C.
railwayStationInCountry
Indicates that a railway station is located within the borders of a specified country.
-
D.
appliesToRailwayNetwork
Indicates that something is relevant or specifically applicable to a railway network as a whole.
-
E.
hasBorderRailConnectionWith
Indicates that two places are directly connected to each other by a cross-border railway line or service.
- F. None of above.
Provenance (4 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_6a01ca0db6f08190bed479584114e63d |
completed | May 11, 2026, 12:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a2eb12eb4788190b785ee2ae0f51a2b |
completed | June 14, 2026, 1:48 p.m. |
| PD | Predicate disambiguation | batch_6a01c96ff4a08190a4fbf0cebbda95b4 |
completed | May 11, 2026, 12:20 p.m. |
Created at: April 30, 2026, 11:49 p.m.