Triple
T38243523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pont Samson |
E1013831
|
entity |
| Predicate | catégorieWikipédiaPotentielle |
P22254
|
FINISHED |
| Object | Pont en Normandie |
—
|
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: Pont en Normandie | Statement: [Pont Samson, catégorieWikipédiaPotentielle, Pont en Normandie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: catégorieWikipédiaPotentielle Context triple: [Pont Samson, catégorieWikipédiaPotentielle, Pont en Normandie]
-
A.
canonicalCategory
Indicates that an entity is assigned to its primary or standard category within a classification system.
-
B.
PSUCategory
Indicates that an entity belongs to, or is classified under, a particular power supply unit (PSU) category.
-
C.
commonsCategory
chosen
Indicates that an entity is associated with a specific media or topic category on Wikimedia Commons.
-
D.
notableParallelCategory
Indicates that one category is recognized as a significant parallel or closely corresponding counterpart to another category.
-
E.
coreCategory
Indicates that one entity is the primary or fundamental category to which another entity belongs or is classified under.
- 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_69f76dd7e89c8190b7866bc85aea521b |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcc3321ef081908023590ba70ba0cf |
completed | May 7, 2026, 4:52 p.m. |
| PD | Predicate disambiguation | batch_69fcb0fdc6e08190b05e894c59481a0d |
completed | May 7, 2026, 3:34 p.m. |
Created at: May 3, 2026, 4:30 p.m.