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.