Triple
T20893012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tang |
E514455
|
entity |
| Predicate | hasJyutping |
P52960
|
FINISHED |
| Object | tong4 |
—
|
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: tong4 | Statement: [Tang, hasJyutping, tong4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasJyutping Context triple: [Tang, hasJyutping, tong4]
-
A.
cantoneseJyutping
chosen
Indicates that an entity’s name or term is represented using the Cantonese Jyutping romanization system.
-
B.
hasKanjiReading
Indicates that a written kanji character is associated with a specific reading or pronunciation.
-
C.
hasHokkienReading
Indicates that an entity is associated with a specific reading or pronunciation in the Hokkien language.
-
D.
hasMandarinReading
Indicates that an entity is associated with a specific reading or pronunciation in Mandarin Chinese.
-
E.
hasJapaneseText
Indicates that an entity contains or is associated with text written in the Japanese language.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05fecd88190905a0ea80a24406a |
completed | April 21, 2026, 1:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a8dc148190b33ff51894e2a8f9 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:46 p.m.