Triple
T27422856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Census Bureau Moore County region |
E693092
|
entity |
| Predicate | dataCollectionType |
P4241
|
FINISHED |
| Object | decennial census |
—
|
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: decennial census | Statement: [United States Census Bureau Moore County region, dataCollectionType, decennial census]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dataCollectionType Context triple: [United States Census Bureau Moore County region, dataCollectionType, decennial census]
-
A.
dataTypeCollected
chosen
Indicates that a specific type or category of data is gathered or recorded in the context of an entity or process.
-
B.
dataCollectionLevel
Indicates the extent or granularity at which data is gathered or recorded within a given context or system.
-
C.
dataTypes
Indicates that one entity specifies or defines the kinds or formats of data that are valid or expected for another entity.
-
D.
dataCollectionLocation
Indicates the place or setting where data is gathered, recorded, or measured.
-
E.
dataTypeContributed
Indicates that an entity has provided or supplied a particular type or category of data.
- 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_69ef5208617081908f731d312e0fd1bc |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62d1e948c8190aadd4607ec8f91db |
completed | May 2, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 12:36 p.m.