Triple
T27305288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nunapitchuk, Alaska |
E689034
|
entity |
| Predicate | partOfCensusAreaType |
P88971
|
FINISHED |
| Object | unorganized borough of Alaska |
—
|
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: unorganized borough of Alaska | Statement: [Nunapitchuk, Alaska, partOfCensusAreaType, unorganized borough of Alaska]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: partOfCensusAreaType Context triple: [Nunapitchuk, Alaska, partOfCensusAreaType, unorganized borough of Alaska]
-
A.
censusSubdivisionType
Indicates the specific administrative or geographic category assigned to a census subdivision (e.g., city, town, rural area) within a census system.
-
B.
censusDivisionType
chosen
Indicates the classification of a census division according to its official administrative or statistical type.
-
C.
localGovernmentAreaType
Indicates the specific classification or category of a local government area within an administrative or governmental hierarchy.
-
D.
typeOfDistrict
Indicates the specific category or classification to which a given district belongs.
-
E.
typeOfAreaRepresented
Indicates that one entity specifies the kind or category of area that another entity represents.
- 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_69ef355b931c8190a63cafaf7bcc008b |
completed | April 27, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69fd474b7e788190a9bb9b542d878f60 |
completed | May 8, 2026, 2:15 a.m. |
| PD | Predicate disambiguation | batch_69fd46d8b2f0819099d92d72c902f60e |
completed | May 8, 2026, 2:13 a.m. |
Created at: April 27, 2026, 11:24 a.m.