Triple
T28651772
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fóshān |
E725219
|
entity |
| Predicate | representsChineseCharacters |
P63661
|
FINISHED |
| Object | 佛山 |
—
|
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: 佛山 | Statement: [Fóshān, representsChineseCharacters, 佛山]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: representsChineseCharacters Context triple: [Fóshān, representsChineseCharacters, 佛山]
-
A.
canRepresentMultipleChineseCharacters
Indicates that a given form (such as a sound, syllable, or written unit) is capable of corresponding to more than one distinct Chinese character.
-
B.
usedChineseCharacters
Indicates that one entity employed or wrote using Chinese characters in relation to another entity or context.
-
C.
representsForCharacters
Indicates that one entity performs a representation or advocacy role on behalf of specific characters.
-
D.
correspondsToChineseCharacter
chosen
Indicates that one entity is the equivalent or representation of a specific Chinese written character.
-
E.
characterUnicodeSimplified
Indicates that one entity is the simplified-Unicode character form corresponding to another character 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69fcef654d588190b29ecc76678d1aa0 |
completed | May 7, 2026, 8 p.m. |
| PD | Predicate disambiguation | batch_69fcecdb97f48190b382b7d13be92dc0 |
completed | May 7, 2026, 7:49 p.m. |
Created at: April 28, 2026, 4:52 a.m.