Triple
T6373636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taizhou |
E143408
|
entity |
| Predicate | hasRegionCodeType |
P3820
|
FINISHED |
| Object | prefecture-level city code |
—
|
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: prefecture-level city code | Statement: [Taizhou, hasRegionCodeType, prefecture-level city code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRegionCodeType Context triple: [Taizhou, hasRegionCodeType, prefecture-level city code]
-
A.
hasRegionCode
Indicates that an entity is associated with a specific regional identifier or code.
-
B.
regionCodeType
chosen
Indicates the classification or format type used for a given region code within a coding or identification system.
-
C.
hasPrimaryCountryCode
Indicates that an entity is associated with its main or officially designated country code.
-
D.
hasAreaCodeType
Indicates that an entity’s area code is associated with a specific type or classification of area code.
-
E.
ISO3166-2RegionCode
Indicates the standardized ISO 3166-2 code that specifies the particular primary administrative subdivision (such as a state, province, or region) to which an entity belongs.
- 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_69c008d9f4348190ab598a2913259a1c |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c068390af08190967a3d25ec9a50e5 |
completed | March 22, 2026, 10:07 p.m. |
| PD | Predicate disambiguation | batch_69c060ee055081908c79a1d151bd74cd |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:33 p.m.