Triple

T27542004
Position Surface form Disambiguated ID Type / Status
Subject 客家话 E695260 entity
Predicate 语言分支 P1967 FINISHED
Object 汉语
汉语是以汉族为主要使用者、拥有多种方言和悠久文字传统的汉藏语系语言。
 E181408 NE FINISHED

How this triple was built (3 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: 汉语 | Statement: [客家话, 语言分支, 汉语]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: 汉语
Triple: [客家话, 语言分支, 汉语]
Generated description
汉语是以汉族为主要使用者、拥有多种方言和悠久文字传统的汉藏语系语言。
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: 语言分支
Context triple: [客家话, 语言分支, 汉语]
  • A. languageBranch chosen
    Indicates that one language belongs to, or is classified under, a broader linguistic branch or subgroup.
  • B. serviceBranchLanguage
    Indicates the language or languages used or officially recognized by a particular branch of a service (such as a military or organizational branch).
  • C. languageFamilyBranchOf
    Indicates that one language family branch is a sub-group or subdivision within a larger language family.
  • D. possibleLanguageBranch
    Indicates that one entity may belong to, derive from, or be classified under the language branch represented by the other entity, without asserting this relationship as certain.
  • E. linguisticClassification
    Indicates the relationship by which an entity is categorized according to its language or linguistic type.
  • F. None of above.

Provenance (6 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_69ef5386c3e08190bfe33aa326e1f72b completed April 27, 2026, 12:16 p.m.
NER Named-entity recognition batch_69f62f5ec8b481909241271f7d602dc9 completed May 2, 2026, 5:07 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12c5c0f60c8190b0507205313d9a59 completed May 24, 2026, 9:32 a.m.
NEDg Description generation batch_6a12c6e244108190940a87f7158f4912 completed May 24, 2026, 9:37 a.m.
NED2 Entity disambiguation (via description) batch_6a12cb0f77248190a107c7cc99767cf6 completed May 24, 2026, 9:55 a.m.
PD Predicate disambiguation batch_69f623ac3a9c8190a6ee0c137b09e4b0 completed May 2, 2026, 4:17 p.m.
Created at: April 27, 2026, 1:31 p.m.