Triple
T16704776
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chan (surname 詹) |
E405939
|
entity |
| Predicate | sharesRomanizationPatternWith |
P38294
|
FINISHED |
| Object | other Cantonese surnames ending in -an |
—
|
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: other Cantonese surnames ending in -an | Statement: [Chan (surname 詹), sharesRomanizationPatternWith, other Cantonese surnames ending in -an]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesRomanizationPatternWith Context triple: [Chan (surname 詹), sharesRomanizationPatternWith, other Cantonese surnames ending in -an]
-
A.
sharesRomanizationWith
Indicates that two distinct written forms are pronounced the same way when transliterated into a shared Romanization system.
-
B.
sharesNamePatternWith
chosen
Indicates that two entities have names that follow the same or a very similar structural or stylistic pattern.
-
C.
hasRomanizationOf
Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
-
D.
sharesSpellingWith
Indicates that two entities have identical or substantially identical written forms (i.e., they are spelled the same way).
-
E.
sharesCharacterWith
Indicates that two entities have at least one character (such as a letter, symbol, or glyph) in common.
- 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_69d8838db21081909589220fd71440a4 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e3833496dc8190ae4b4a03ba04d69d |
completed | April 18, 2026, 1:12 p.m. |
| PD | Predicate disambiguation | batch_69e319c379f88190ac0adf812486f598 |
completed | April 18, 2026, 5:42 a.m. |
Created at: April 10, 2026, 5:19 a.m.