Triple
T28373843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 竹山县 |
E718702
|
entity |
| Predicate | 所属省级行政区 |
P88409
|
FINISHED |
| Object | 湖北省 |
—
|
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: 湖北省 | Statement: [竹山县, 所属省级行政区, 湖北省]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属省级行政区 Context triple: [竹山县, 所属省级行政区, 湖北省]
-
A.
hasProvinceLevelUnit
Indicates that one administrative or territorial entity possesses or contains a sub-unit at the province (or equivalent) level.
-
B.
comprisesProvince
Indicates that a larger territorial or administrative unit is made up of, or includes within its boundaries, a specific province.
-
C.
associatedProvinceOrState
chosen
Indicates that one entity is linked or related to a specific province or state as its relevant administrative region.
-
D.
rankInChineseAdministrativeHierarchy
Indicates the relative level or position an administrative unit holds within the formal hierarchy of Chinese government administration.
-
E.
baseProvince
Indicates that one administrative or territorial unit serves as the primary or originating province associated with another entity.
- 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_69eff6ee5afc8190bd7375a29f0cc6c6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5c0ba081908d836393db68b842 |
completed | May 2, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:01 a.m.