Triple
T32792987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quiet Night Thought |
E838679
|
entity |
| Predicate | secondLineInChinese |
P63341
|
FINISHED |
| Object | 疑是地上霜 |
—
|
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: 疑是地上霜 | Statement: [Quiet Night Thought, secondLineInChinese, 疑是地上霜]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondLineInChinese Context triple: [Quiet Night Thought, secondLineInChinese, 疑是地上霜]
-
A.
thirdLineInChinese
Indicates that one entity is the third line (or row) in a sequence of lines when written or displayed in Chinese.
-
B.
secondInLine
chosen
Indicates that one entity occupies the second position in a sequence or queue immediately following the first.
-
C.
secondaryLine
Indicates that something serves as a secondary or auxiliary line in relation to a primary or main line.
-
D.
secondLineTransition
Indicates a transition or change that occurs specifically in the second line of a sequence, text, or structured representation.
-
E.
secondSeries
Indicates that one entity is the second installment or season in a series relative to 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_69f3493c7f6881908edf2aa13631d1e0 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69feb5e66224819083b87c3707a5a5e0 |
completed | May 9, 2026, 4:19 a.m. |
| PD | Predicate disambiguation | batch_69feb3bd700c8190991ed200cd3c04db |
completed | May 9, 2026, 4:10 a.m. |
Created at: May 1, 2026, 1:14 a.m.