Triple
T35755640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kagi |
E1033438
|
entity |
| Predicate | correspondsToChineseName |
P4878
|
FINISHED |
| Object | Chiayi |
E1144715
|
NE 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: Chiayi | Statement: [Kagi, correspondsToChineseName, Chiayi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: correspondsToChineseName Context triple: [Kagi, correspondsToChineseName, Chiayi]
-
A.
correspondsToChineseSurname
Indicates that one entity is the Chinese surname equivalent or counterpart of another entity.
-
B.
correspondsToChineseCharacter
Indicates that one entity is the equivalent or representation of a specific Chinese written character.
-
C.
nameInChinese
chosen
Indicates that an entity has a specific written name or label expressed in the Chinese language.
-
D.
hasEthnonymInChinese
Indicates that an entity has a specific ethnonym (name for an ethnic group or people) expressed in the Chinese language.
-
E.
correspondsToSurname
Indicates that one entity is the surname or family name associated with, matching, or representing the other entity.
- F. None of above.
Provenance (4 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_69f76e1262f48190a313318665acc189 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a394d1804e881908789c4c222fbe0a3 |
completed | June 22, 2026, 2:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: May 3, 2026, 4:06 p.m.