Triple
T32413179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eighteenth Amendment to the Constitution of Pakistan |
E828277
|
entity |
| Predicate | numberOfClauses |
P203618
|
FINISHED |
| Object | over 100 clauses |
—
|
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: over 100 clauses | Statement: [Eighteenth Amendment to the Constitution of Pakistan, numberOfClauses, over 100 clauses]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfClauses Context triple: [Eighteenth Amendment to the Constitution of Pakistan, numberOfClauses, over 100 clauses]
-
A.
numberOfPropositions
Indicates the total count of distinct propositions associated with or contained within a given entity or context.
-
B.
clauseNumber
Indicates the specific numbered position or identifier assigned to a clause within a larger document or agreement.
-
C.
numberOfTruths
Indicates the quantity of statements or propositions that are true within a given context or set.
-
D.
numberOfPredications
Indicates the total count of individual predication instances or assertions associated with a given subject or context.
-
E.
clauseLength
Indicates the length or number of components in a clause within a larger structure or statement.
- 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_69f34919f300819092b541c6277cd68a |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_6a01b3af7b908190b4675c85d32d106c |
completed | May 11, 2026, 10:47 a.m. |
| PD | Predicate disambiguation | batch_6a01b35813c081908e484b2b9ca5dd05 |
completed | May 11, 2026, 10:45 a.m. |
| PDg | Predicate description generation | batch_6a01b3ae7f948190b93fbe0add0dbcec |
completed | May 11, 2026, 10:47 a.m. |
Created at: May 1, 2026, 12:53 a.m.