Triple
T12839621
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paris Métro Gare de Lyon |
E307013
|
entity |
| Predicate | line14PlatformsOpened |
P97617
|
FINISHED |
| Object | 1998-10-15 |
—
|
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: 1998-10-15 | Statement: [Paris Métro Gare de Lyon, line14PlatformsOpened, 1998-10-15]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: line14PlatformsOpened Context triple: [Paris Métro Gare de Lyon, line14PlatformsOpened, 1998-10-15]
-
A.
platformsForLine14
Indicates that the subject provides or contains platforms that serve line 14 (such as a transit or railway line).
-
B.
line11PlatformsOpeningDate
Indicates the date on which the platforms for line 11 were opened for use.
-
C.
line9PlatformsOpeningDate
Indicates the date on which the platforms for line 9 were first opened for use.
-
D.
line14OpeningDate
chosen
Indicates the date on which line 14 was first opened or began operation.
-
E.
ElizabethLinePlatformsOpened
Indicates that the platforms associated with the Elizabeth Line have been officially opened for public use.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9714208f881908f7f8a921362909a |
completed | April 10, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69d96fa08cd481909a946046ba63809f |
completed | April 10, 2026, 9:46 p.m. |
Created at: April 9, 2026, 5:35 p.m.