Triple
T9344138
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Corsica |
E224839
|
entity |
| Predicate | constitutionCharacter |
P87631
|
FINISHED |
| Object | democratic |
—
|
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: democratic | Statement: [Kingdom of Corsica, constitutionCharacter, democratic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constitutionCharacter Context triple: [Kingdom of Corsica, constitutionCharacter, democratic]
-
A.
constitutionalName
Indicates the official name of an entity as defined or recognized in its constitution or foundational legal document.
-
B.
constitutionLikeDocument
Indicates that one entity is a document that functions similarly to a constitution for another entity, outlining fundamental principles, structures, or governing rules.
-
C.
constitutionalChapter
Indicates that one entity is a specific chapter or section within a constitution that organizes or governs the other entity.
-
D.
constitutionArticle
Indicates that one entity is an article or specific provision contained within the constitution represented by the other entity.
-
E.
constitutionalCategory
Indicates the classification of something according to its constitutional or structural type or category.
- 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_69ca842993248190a79ab06968994b86 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd4bb244e88190b269e0bc997f066a |
completed | April 1, 2026, 4:45 p.m. |
| PD | Predicate disambiguation | batch_69cc7a66aef08190b8d668cff5b04f5f |
completed | April 1, 2026, 1:52 a.m. |
| PDg | Predicate description generation | batch_69cc94b796788190816b71b1e9996288 |
completed | April 1, 2026, 3:44 a.m. |
Created at: March 30, 2026, 7:40 p.m.