Triple
T27601254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ningyang County |
E700049
|
entity |
| Predicate | prefectureLevelCitySeat |
P96684
|
FINISHED |
| Object | Tai'an |
—
|
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: Tai'an | Statement: [Ningyang County, prefectureLevelCitySeat, Tai'an]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: prefectureLevelCitySeat Context triple: [Ningyang County, prefectureLevelCitySeat, Tai'an]
-
A.
prefectureCapital
Indicates that a city serves as the administrative capital of a given prefecture.
-
B.
governingPrefecturalCapital
Indicates that one entity serves as the administrative capital governing a particular prefecture.
-
C.
prefecture-levelCity
chosen
Indicates that one entity is a city that holds prefecture-level administrative status in relation to another entity (typically a higher-level region or governing structure).
-
D.
subprefectureCapital
Indicates that one entity serves as the administrative capital or seat of government for a given subprefecture.
-
E.
isPrefecturalCityOf
Indicates that a city holds the administrative status of a prefecture-level city within a given region or country.
- 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_69ef6a4e2e208190b63b7268f405785c |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 2:08 p.m.