Triple
T32272646
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mexican federal system |
E824454
|
entity |
| Predicate | currentFrameworkFrom |
P2450
|
FINISHED |
| Object | Constitution of 1917 |
—
|
NE NERFINISHED |
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: Constitution of 1917 | Statement: [Mexican federal system, currentFrameworkFrom, Constitution of 1917]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: currentFrameworkFrom Context triple: [Mexican federal system, currentFrameworkFrom, Constitution of 1917]
-
A.
currentFrameworkBasedOn
chosen
Indicates that the current framework is derived from, built upon, or structured according to another underlying framework.
-
B.
parentFramework
Indicates that one framework serves as the higher-level or containing framework from which another framework is derived, organized, or structured.
-
C.
frameworkName
Indicates that a specific framework is identified by the given name.
-
D.
frameworkFor
Indicates that one entity serves as a supporting structure, system, or basis that organizes, guides, or enables the development or functioning of another entity.
-
E.
adoptedFrameworkType
Indicates that one entity has chosen and is using a particular framework type as its adopted standard or approach.
- 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_69f3490e73588190915f282edd105772 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69feafa1ba0081909013800b85a9f613 |
completed | May 9, 2026, 3:53 a.m. |
| PD | Predicate disambiguation | batch_69feae58d62c81909d031f3df8992883 |
completed | May 9, 2026, 3:47 a.m. |
Created at: May 1, 2026, 12:42 a.m.