Triple
T24070598
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States Census Bureau places in New York |
E596213
|
entity |
| Predicate | mapsAvailableThrough |
P58705
|
FINISHED |
| Object | Census Bureau online mapping tools |
—
|
NE NERFINISHED |
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: Census Bureau online mapping tools | Statement: [United States Census Bureau places in New York, mapsAvailableThrough, Census Bureau online mapping tools]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: mapsAvailableThrough Context triple: [United States Census Bureau places in New York, mapsAvailableThrough, Census Bureau online mapping tools]
-
A.
mappingAvailableTo
Indicates that a mapping or correspondence exists and is accessible between one entity and another.
-
B.
mapAvailability
chosen
Indicates that a map is accessible or provided for use in a given context or location.
-
C.
mapsType
Indicates that one entity serves as a mapping whose values or outputs are of the specified type.
-
D.
mapsIncluded
Indicates that one map or mapping is contained within, or is a subset of, another map or mapping.
-
E.
mapsIn
Indicates that one entity is contained or represented within another entity as part of a mapping or map-like relationship.
- 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_69e288c25c008190850cf447940ab181 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1db191d288190af438be742e02252 |
completed | April 29, 2026, 10:19 a.m. |
| PD | Predicate disambiguation | batch_69f1764b1d4c8190b12590c6339c31c1 |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 10:41 p.m.