Triple
T20615827
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canal du Centre |
E506561
|
entity |
| Predicate | hasModernSection |
P140792
|
FINISHED |
| Object | new Canal du Centre |
—
|
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: new Canal du Centre | Statement: [Canal du Centre, hasModernSection, new Canal du Centre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasModernSection Context triple: [Canal du Centre, hasModernSection, new Canal du Centre]
-
A.
hasModernMaterial
Indicates that an entity incorporates or is made from contemporary, recently developed, or non-traditional materials.
-
B.
hasModernEditor
Indicates that an entity is associated with, or has been prepared or revised by, a contemporary editor.
-
C.
isModern
Indicates that something belongs to, reflects, or is characteristic of the contemporary or recent period, especially in style, design, or thinking.
-
D.
hasModernSquare
Indicates that an entity possesses or includes a square-shaped feature designed or styled in a modern way.
-
E.
hasModernFormulationIn
Indicates that something has a contemporary or updated version expressed or formulated within a specified context, framework, or medium.
- 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_69e0b4bc90988190ac360aaf645efc1d |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6aadbb3ac81908145f57fd6a94256 |
completed | April 20, 2026, 10:38 p.m. |
| PD | Predicate disambiguation | batch_69e5a00c43308190b7ea58d559257e07 |
completed | April 20, 2026, 3:39 a.m. |
| PDg | Predicate description generation | batch_69e5a6a9f3f88190b961db9aca36f7da |
completed | April 20, 2026, 4:08 a.m. |
Created at: April 16, 2026, 11:41 a.m.