Triple
T20053540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Ireland (Temporary Provisions) Act 1972 |
E499265
|
entity |
| Predicate | typeOfRuleIntroduced |
P133790
|
FINISHED |
| Object | direct rule |
—
|
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: direct rule | Statement: [Northern Ireland (Temporary Provisions) Act 1972, typeOfRuleIntroduced, direct rule]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfRuleIntroduced Context triple: [Northern Ireland (Temporary Provisions) Act 1972, typeOfRuleIntroduced, direct rule]
-
A.
typeOfRule
Indicates that one rule is classified as a specific kind or category of another, more general rule.
-
B.
typeOfRules
Indicates that one entity specifies or categorizes the kind or category of rules that apply to or are associated with another entity.
-
C.
natureOfRule
chosen
Indicates the fundamental type or character of a rule, specifying what kind of rule it is or how it functions within a system.
-
D.
isRuleGoverned
Indicates that an entity’s behavior, structure, or operation is determined and constrained by explicit rules or formal regulations.
-
E.
styleOfRule
Indicates the stylistic or formatting convention that a particular rule follows or is expressed in.
- 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_69da6276bcf48190aabbf279192a5fb4 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6633043a481908359ad232607182a |
completed | April 20, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69e54cee7a5c819084ae4ff26419833f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:38 p.m.