Triple
T3353832
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bois de Vincennes |
E70558
|
entity |
| Predicate | createdAsPublicPark |
P47427
|
FINISHED |
| Object | 19th century |
—
|
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: 19th century | Statement: [Bois de Vincennes, createdAsPublicPark, 19th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: createdAsPublicPark Context triple: [Bois de Vincennes, createdAsPublicPark, 19th century]
-
A.
separatedAsIndependentPark
Indicates that a specific area has been designated and treated as an independent park, distinct and administratively separated from surrounding or previously associated parkland.
-
B.
originalParkName
Indicates the relationship where a park is associated with its original or former official name.
-
C.
createdAsGarden
Indicates that something was brought into existence or established specifically in the form or function of a garden.
-
D.
isPublicParkComponent
Indicates that something is a constituent element or feature that forms part of a public park.
-
E.
openedAsStatePark
Indicates that a location or area was officially inaugurated and made available to the public as a state park.
- F. None of above. chosen
Provenance (4 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_69ad85a4ef7c8190a29e2bbd6fa454e4 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb24036848190bac779d17dfdce3b |
completed | March 8, 2026, 5:30 p.m. |
| PD | Predicate disambiguation | batch_69ada42fbe7c8190b9f185b5ab985f17 |
completed | March 8, 2026, 4:30 p.m. |
| PDg | Predicate description generation | batch_69ada52716ec81908e89688a81039394 |
completed | March 8, 2026, 4:34 p.m. |
Created at: March 8, 2026, 3:13 p.m.