Triple
T28822938
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris–Marseille |
E727820
|
entity |
| Predicate | partlyUsesLine |
P14437
|
FINISHED |
| Object | LGV Méditerranée |
—
|
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: LGV Méditerranée | Statement: [Paris–Marseille, partlyUsesLine, LGV Méditerranée]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partlyUsesLine Context triple: [Paris–Marseille, partlyUsesLine, LGV Méditerranée]
-
A.
lineUse
Indicates how a particular line (such as a route, track, or service line) is utilized or purposed within a system or network.
-
B.
lineUses
chosen
Indicates that a particular line (such as a route, service, or connection) makes use of or is implemented using a specified resource, infrastructure, or element.
-
C.
usesLineCharacteristic
Indicates that one entity employs or is based on a specific characteristic or property of a line.
-
D.
formsPartOfLine
Indicates that one element constitutes a segment or component belonging to a larger line.
-
E.
usesLineCode
Indicates that one entity employs or references a specific line code as part of its operation, identification, or communication.
- 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_69f0319d09088190bbf14cdf1987792a |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f6617ba4a88190bfc5c305acb4f93f |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 6:35 a.m.