Triple
T29060559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Villejuif – Léo Lagrange |
E735515
|
entity |
| Predicate | isOnBranchOfLine7 |
P125739
|
FINISHED |
| Object | Villejuif branch |
—
|
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: Villejuif branch | Statement: [Villejuif – Léo Lagrange, isOnBranchOfLine7, Villejuif branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isOnBranchOfLine7 Context triple: [Villejuif – Léo Lagrange, isOnBranchOfLine7, Villejuif branch]
-
A.
isOnBranchOfLine
chosen
Indicates that something is located on or belongs to a specific branch of a larger line or route.
-
B.
isBetweenStationsOnLine
Indicates that something is located or occurs between two stations along the same transit line.
-
C.
isOnSuburbanLine
Indicates that something (typically a transit service or stop) operates on or belongs to a suburban railway or transit line.
-
D.
isOnEastWestTrunkLine
Indicates that something is located on, or directly aligned with, a primary east–west transportation or utility trunk line.
-
E.
isJunctionOnLine
Indicates that a particular junction lies on, or is part of, a specified 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_69f077e85498819088b65186550da8cd |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f6609704a88190b0e03463d30b473f |
completed | May 2, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 10:15 a.m.