Triple
T28651773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fóshān |
E725219
|
entity |
| Predicate | correspondsToCity |
P86374
|
FINISHED |
| Object | Foshan |
—
|
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: Foshan | Statement: [Fóshān, correspondsToCity, Foshan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondsToCity Context triple: [Fóshān, correspondsToCity, Foshan]
-
A.
refersToCityAs
chosen
Indicates that one entity designates, mentions, or identifies another entity specifically as a city.
-
B.
refersToCityOn
Indicates that one entity makes reference to, or is specifically about, a particular city located on a given date or temporal context.
-
C.
hasAssociatedCity
Indicates that one entity is linked or related to a specific city, typically as its location, base, or primary area of association.
-
D.
refersToCityWithAttribute
Indicates that one entity refers to a city that possesses a specified attribute or set of attributes.
-
E.
coversCity
Indicates that one entity extends over, includes, or geographically encompasses the area of a specified city.
- 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f68f670b608190a0b6ab60d722b4e0 |
completed | May 2, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69f68b78f29481908cc8f390496dee97 |
completed | May 2, 2026, 11:40 p.m. |
Created at: April 28, 2026, 4:52 a.m.