Triple
T1950067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States constitutional amendments |
E42137
|
entity |
| Predicate | numberOfRatifiedAmendments |
P1039
|
FINISHED |
| Object | 27 |
—
|
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: 27 | Statement: [United States constitutional amendments, numberOfRatifiedAmendments, 27]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfRatifiedAmendments Context triple: [United States constitutional amendments, numberOfRatifiedAmendments, 27]
-
A.
amendmentCount
chosen
Indicates the number of amendments that have been made to a given item, document, or entity.
-
B.
constitutionalAmendmentNumber
Indicates the specific numerical designation assigned to a particular constitutional amendment within a legal or constitutional framework.
-
C.
majorAmendmentYear
Indicates the year in which a significant or major amendment was made to something (such as a document, law, or agreement).
-
D.
hasAmendments
Indicates that one entity (such as a document, law, or agreement) includes or is associated with one or more modifications, changes, or additions made after its original creation.
-
E.
canAmendConstitution
Indicates that an entity has the authority or power to modify or revise a constitution.
- 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_69a8870e08fc8190a319cbf2600db15f |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb332b014819085bfc88d66cfc10a |
completed | March 7, 2026, 5:10 a.m. |
| PD | Predicate disambiguation | batch_69abaff3eda88190b643994cb4dfb8df |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:36 p.m.