Triple

T23781488
Position Surface form Disambiguated ID Type / Status
Subject Yalu River Broken Bridge E587825 entity
Predicate numberOfSpansRemainingOnChineseSide P153910 FINISHED
Object about half of original spans 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: about half of original spans | Statement: [Yalu River Broken Bridge, numberOfSpansRemainingOnChineseSide, about half of original spans]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: numberOfSpansRemainingOnChineseSide
Context triple: [Yalu River Broken Bridge, numberOfSpansRemainingOnChineseSide, about half of original spans]
  • A. lengthInChina
    Indicates that the specified length or distance is measured according to standards, units, or conditions applicable within China.
  • B. numberOfSpans
    Indicates the total count of distinct spans or segments associated with an entity or within a specified context.
  • C. hasMultipleChineseCharacters
    Indicates that the referenced item consists of more than one Chinese character.
  • D. numberOfSideSpans
    Indicates the count of side spans associated with a primary span or structure.
  • E. limitedChinese
    Indicates that the relationship or action is restricted, constrained, or only partially applicable within a Chinese-language or China-related context.
  • F. None of above. chosen

Provenance (4 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_69e2490f4ad48190b690878eec3596c6 completed April 17, 2026, 2:51 p.m.
NER Named-entity recognition batch_69f1c62d7c608190b5fd0cf35f5faf42 completed April 29, 2026, 8:49 a.m.
PD Predicate disambiguation batch_69f155f79e34819080f9ddb972b34deb completed April 29, 2026, 12:51 a.m.
PDg Predicate description generation batch_69f15ed138f88190a8ae555422978908 completed April 29, 2026, 1:28 a.m.
Created at: April 17, 2026, 7:16 p.m.