Triple
T735488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chan |
E14920
|
entity |
| Predicate | romanizationSystem |
P6517
|
FINISHED |
| Object | Cantonese-based romanization |
—
|
LITERAL 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: Cantonese-based romanization | Statement: [Chan, romanizationSystem, Cantonese-based romanization]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: romanizationSystem Context triple: [Chan, romanizationSystem, Cantonese-based romanization]
-
A.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
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.
notationSystem
chosen
Indicates a relationship where one entity is the system or method of notation used to represent or encode another entity.
-
D.
hasRomanizationContrast
Indicates that there is a meaningful difference between two or more romanized representations of the same original form.
-
E.
writingSystem
Indicates that one entity is the script or system of written symbols used to represent the language or content of another 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_69a4934d9930819099eed80096b0597d |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a66820548190b373deb117187c2c |
completed | March 1, 2026, 8:49 p.m. |
| PD | Predicate disambiguation | batch_69a4a4fafee081909bf356854c09aaff |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.