Triple
T37199705
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | arrondissement of Évreux |
E921693
|
entity |
| Predicate | isLevelIn |
P187520
|
FINISHED |
| Object | French territorial administration |
—
|
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: French territorial administration | Statement: [arrondissement of Évreux, isLevelIn, French territorial administration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLevelIn Context triple: [arrondissement of Évreux, isLevelIn, French territorial administration]
-
A.
hasLevel
Indicates that an entity possesses or is associated with a particular degree, rank, or stage within an ordered scale or hierarchy.
-
B.
containsLevel
Indicates that one entity includes or encompasses a specific level or layer within its structure or hierarchy.
-
C.
meetsAtLevel
Indicates that two or more entities encounter or interact with each other at a specific hierarchical, structural, or progression level.
-
D.
isElevatedOrAtGradeIn
Indicates that one entity is positioned either above ground level (elevated) or directly at ground level (at grade) within the context of another entity or environment.
-
E.
coversLevel
Indicates that one entity includes or encompasses a particular level or layer of another entity or system.
- 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_69f76ea313a08190a54404cd1e47da90 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb55de3b9c8190a7656aeab3c3ffbc |
completed | May 6, 2026, 2:53 p.m. |
| PD | Predicate disambiguation | batch_69fb35bc92e08190bff447624e2df791 |
completed | May 6, 2026, 12:36 p.m. |
| PDg | Predicate description generation | batch_69fb55dc36d08190a0634fa680e13114 |
completed | May 6, 2026, 2:53 p.m. |
Created at: May 3, 2026, 4:15 p.m.