Triple
T5123508
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diocese of Sodor and Man |
E115526
|
entity |
| Predicate | hasCivilContext |
P62652
|
FINISHED |
| Object | Isle of Man is a Crown Dependency |
—
|
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: Isle of Man is a Crown Dependency | Statement: [Diocese of Sodor and Man, hasCivilContext, Isle of Man is a Crown Dependency]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCivilContext Context triple: [Diocese of Sodor and Man, hasCivilContext, Isle of Man is a Crown Dependency]
-
A.
hasCivilSection
Indicates that one legal document, case, or record includes or is associated with a specific civil law section or provision.
-
B.
haveCivilLaw
Indicates that an entity is subject to, governed by, or operates under a civil law legal system.
-
C.
hasCivilArea
Indicates that an administrative or political entity encompasses or is associated with a specific civil (local administrative) area.
-
D.
hasCivilDivision
Indicates that one administrative or political entity is subdivided into, or is associated with, a specific civil division (such as a county, district, or municipality).
-
E.
handlesCivilMatter
Indicates that an entity is responsible for dealing with or adjudicating civil (non-criminal) legal matters involving disputes between parties.
- 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_69bd4442ade0819087b9461f892b206b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd7d5a23908190a24e79d1b29d6fcf |
completed | March 20, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69bd77aa68b88190a50dd736a72d2901 |
completed | March 20, 2026, 4:36 p.m. |
| PDg | Predicate description generation | batch_69bd7d5906d88190b805977e5a05767a |
completed | March 20, 2026, 5:01 p.m. |
Created at: March 20, 2026, 1:42 p.m.