Triple
T33074859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Havre–Caumartin (Paris Métro) |
E846330
|
entity |
| Predicate | line9PlatformsOpened |
P28542
|
FINISHED |
| Object | 1923-06-10 |
—
|
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: 1923-06-10 | Statement: [Havre–Caumartin (Paris Métro), line9PlatformsOpened, 1923-06-10]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: line9PlatformsOpened Context triple: [Havre–Caumartin (Paris Métro), line9PlatformsOpened, 1923-06-10]
-
A.
line9PlatformsOpeningDate
chosen
Indicates the date on which the platforms for line 9 were first opened for use.
-
B.
line7PlatformsOpened
Indicates that the platforms associated with line 7 have been opened for use or made operational.
-
C.
line5PlatformsOpened
Indicates that the platforms associated with line 5 have been opened and are now available for use.
-
D.
line1PlatformsOpened
Indicates that the platforms serving line 1 have been opened and are available for use.
-
E.
line4PlatformsOpened
Indicates that the platforms associated with line 4 have been opened for use or made operational.
- 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_69f3495405b88190967af2157b43b896 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:25 a.m.