Triple
T32792986
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quiet Night Thought |
E838679
|
entity |
| Predicate | firstLineInChinese |
P197547
|
FINISHED |
| Object | 床前明月光 |
—
|
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: 床前明月光 | Statement: [Quiet Night Thought, firstLineInChinese, 床前明月光]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstLineInChinese Context triple: [Quiet Night Thought, firstLineInChinese, 床前明月光]
-
A.
thirdLineInChinese
Indicates that one entity is the third line (or row) in a sequence of lines when written or displayed in Chinese.
-
B.
firstLines
chosen
Indicates that one text, segment, or element constitutes the initial lines or opening portion of another.
-
C.
firstLineTranslation
Indicates that one text is a translation of the first line of another text.
-
D.
firstLineInUrdu
Indicates that the referenced text is the first line of a piece of content when written or displayed in Urdu.
-
E.
firstLineAfrikaans
Indicates that the specified text is the first line of a piece of content when written in Afrikaans.
- 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_6a037cad051c8190b28b354b89208574 |
completed | May 12, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_6a0379f0cbe481909b4b8fc6cbe297f0 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 1, 2026, 1:14 a.m.