Triple
T35169119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swatow |
E1015492
|
entity |
| Predicate | formerTransliterationOf |
P65221
|
FINISHED |
| Object | 汕头 |
—
|
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: 汕头 | Statement: [Swatow, formerTransliterationOf, 汕头]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formerTransliterationOf Context triple: [Swatow, formerTransliterationOf, 汕头]
-
A.
formerTransliteration
chosen
Indicates that one transliteration was previously used for an entity but has since been replaced by a different transliteration.
-
B.
alternativeTransliteration
Indicates that one written form represents an alternative way of transliterating the same original text or name into another script or orthography.
-
C.
typicalTransliterationFrom
Indicates that one string is the standard or most commonly used transliteration of another string from one writing system to another.
-
D.
transliterationNote
Indicates that there is a note or comment specifically about how an entity’s name or text has been transliterated from one writing system to another.
-
E.
hasFormerRomanization
Indicates that an entity was previously written or represented using an earlier or superseded system of Romanized spelling.
- 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_69f76ddbfde081908bffc91572368289 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a00474f08908190bc8ae3b320ec887b |
completed | May 10, 2026, 8:52 a.m. |
| PD | Predicate disambiguation | batch_6a0045dc3bd48190a9e0520f3ef3f067 |
completed | May 10, 2026, 8:46 a.m. |
Created at: May 3, 2026, 4:02 p.m.