Triple
T29520872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Filles du Calvaire (Paris Métro) |
E748928
|
entity |
| Predicate | adjacentStationOnLine8 |
P137236
|
FINISHED |
| Object | République (Paris Métro) |
—
|
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: République (Paris Métro) | Statement: [Filles du Calvaire (Paris Métro), adjacentStationOnLine8, République (Paris Métro)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentStationOnLine8 Context triple: [Filles du Calvaire (Paris Métro), adjacentStationOnLine8, République (Paris Métro)]
-
A.
hasAdjacentStationOnLine8
chosen
Indicates that two stations are directly next to each other along subway Line 8, with no other station between them on that line.
-
B.
adjacentStationOnLineD
Indicates that one station is directly next to another station along line D, with no other stations in between on that line.
-
C.
adjacentStationOnLine
Indicates that one station is directly next to another station along the same transit line, with no other station in between.
-
D.
adjacentStationOnLine9
Indicates that one station is directly next to another station along the route of Line 9, with no other stations in between on that line.
-
E.
adjacentStationOnLineB
Indicates that one station is directly next to another station along line B in the network.
- 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_69f0bd46d99c81908ba9d01cc1dbef7d |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f6fb19063c81909466b329655c8583 |
completed | May 3, 2026, 7:36 a.m. |
| PD | Predicate disambiguation | batch_69f6f969b4cc8190afb473a2d8b110bc |
completed | May 3, 2026, 7:29 a.m. |
Created at: April 28, 2026, 4:41 p.m.