Triple
T31768870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 鄭 |
E810882
|
entity |
| Predicate | romanizedAsInYale |
P135924
|
FINISHED |
| Object | Ceng |
—
|
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: Ceng | Statement: [鄭, romanizedAsInYale, Ceng]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizedAsInYale Context triple: [鄭, romanizedAsInYale, Ceng]
-
A.
romanizedUnder
Indicates that one written form is a romanized representation (using the Latin alphabet) of another form written in a different script.
-
B.
romanizationVariantOf
chosen
Indicates that one written form is a different romanized representation of the same underlying word or expression as another.
-
C.
yueRomanization
Indicates that an entity is represented or written using the Cantonese (Yue) romanization system.
-
D.
romanizedCenter
Indicates that one entity is the central or primary romanized (Latin-script) representation associated with another entity.
-
E.
romanizationType
Indicates the specific system or method used to convert text from one writing system into its Roman (Latin) alphabet representation.
- 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_69f348e463e08190b902d4819195e1f0 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: April 30, 2026, 11:33 p.m.