Triple
T17053712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Indiana superior courts |
E413765
|
entity |
| Predicate | mayHaveDivision |
P90657
|
FINISHED |
| Object | criminal division |
—
|
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: criminal division | Statement: [Indiana superior courts, mayHaveDivision, criminal division]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mayHaveDivision Context triple: [Indiana superior courts, mayHaveDivision, criminal division]
-
A.
containsDivision
chosen
Indicates that one entity includes or encompasses a subdivision or internal division of another entity.
-
B.
hasDivisionCode
Indicates that an entity is associated with a specific division identifier or code within an organizational or classification structure.
-
C.
hasDivisionLevel
Indicates that one entity is associated with a specific hierarchical or organizational division level of another entity.
-
D.
sometimesDividedInto
Indicates that an entity is on some occasions partitioned or separated into distinct parts, sections, or groups, but not always.
-
E.
hasDivisionNames
Indicates that an entity is associated with one or more names of its internal divisions or subunits.
- 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_69d886cde3d481908d4d01ba88ba7eb7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3daa491008190ad013ee37532aa51 |
completed | April 18, 2026, 7:25 p.m. |
| PD | Predicate disambiguation | batch_69e35d60a588819084f53ef9f8b2e7c0 |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:34 a.m.