Triple
T28759529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guan |
E731769
|
entity |
| Predicate | hasVariantSpellingCommonInCantoneseRomanization |
P457
|
FINISHED |
| Object | Kwan |
—
|
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: Kwan | Statement: [Guan, hasVariantSpellingCommonInCantoneseRomanization, Kwan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasVariantSpellingCommonInCantoneseRomanization Context triple: [Guan, hasVariantSpellingCommonInCantoneseRomanization, Kwan]
-
A.
hasVariantSpelling
chosen
Indicates that one term is an alternative spelling form of another term.
-
B.
cantoneseForm
Indicates that one entity is the Cantonese-language form or representation of another entity.
-
C.
cantoneseYaleForm
Indicates the written form of a term using the Yale romanization system for Cantonese pronunciation.
-
D.
cantoneseJyutping
Indicates that an entity’s name or term is represented using the Cantonese Jyutping romanization system.
-
E.
spellingVariantPattern
Indicates a relationship where one form of a word is a systematic spelling variant of another, following a recognizable pattern of orthographic change.
- 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_69f043ed68a881909e858a06bab7a247 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65a6c900881908f18b61273d7bf8d |
completed | May 2, 2026, 8:11 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 6:11 a.m.