Triple
T6690862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Circuit Court for Howard County |
E152621
|
entity |
| Predicate | hasRecordKeeping |
P2722
|
FINISHED |
| Object | court of record with official transcripts |
—
|
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: court of record with official transcripts | Statement: [Circuit Court for Howard County, hasRecordKeeping, court of record with official transcripts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRecordKeeping Context triple: [Circuit Court for Howard County, hasRecordKeeping, court of record with official transcripts]
-
A.
statusRecordedBy
Indicates that the status of an entity was documented or captured by a specific agent or system.
-
B.
recordHeld
chosen
Indicates that one entity possesses or maintains a particular record associated with another entity or context.
-
C.
retentionMethod
Indicates the method or strategy used to retain or keep something (such as data, customers, or resources) over time.
-
D.
recordHeldIn
Indicates that a record is stored, maintained, or kept within a particular location, system, or repository.
-
E.
recordStatus
Indicates the current state or condition of a record within a system or process (e.g., active, inactive, pending, or archived).
- 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_69c6880687b08190805278b504d1c92c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6cd0fa5188190a23281cb09d98139 |
completed | March 27, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69c6ad0d3c1081908dadff7a6a054123 |
completed | March 27, 2026, 4:15 p.m. |
Created at: March 27, 2026, 2:04 p.m.