Triple

T29263516

Position	Surface form	Disambiguated ID	Type / Status
Subject	Kangxi Dictionary	`E741912`	entity
Predicate	isCanonicalSourceFor	`P134129`	FINISHED
Object	Kangxi radical list The Kangxi radical list is the standardized set of 214 Chinese character radicals used as the primary indexing system in traditional Chinese dictionaries and many modern lexicographic works.	`E1860330`	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: Kangxi radical list | Statement: [Kangxi Dictionary, isCanonicalSourceFor, Kangxi radical list]

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: Kangxi radical list
Triple: [Kangxi Dictionary, isCanonicalSourceFor, Kangxi radical list]

Generated description

The Kangxi radical list is the standardized set of 214 Chinese character radicals used as the primary indexing system in traditional Chinese dictionaries and many modern lexicographic works.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: isCanonicalSourceFor
Context triple: [Kangxi Dictionary, isCanonicalSourceFor, Kangxi radical list]

A. isCanonical
Indicates that something represents the standard, authoritative, or officially accepted form within a given context or system.
B. hasCanonicalLanguageSource chosen
Indicates that something is derived from, based on, or defined according to an officially recognized or standard language source.
C. isCanonicalOn
Indicates that something is recognized as the standard or authoritative form of another entity within a given context.
D. isContemporarySourceFor
Indicates that one entity serves as a source of information that originates from the same time period as the other entity or event it documents.
E. isCanonicalWithRespectTo
Indicates that something conforms to, or is expressed in, a standard or authoritative form relative to a specified framework, reference, or set of rules.
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_69f0912065c08190bddd23e20e8ef18e`	completed	April 28, 2026, 10:51 a.m.
NER	Named-entity recognition	`batch_69f664dd47488190946f9a3f9c4a7d24`	completed	May 2, 2026, 8:55 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a25892fe13c8190962b848595233d43`	completed	June 7, 2026, 3:07 p.m.
NEDg	Description generation	`batch_6a258d4474448190844fdc2216ecbd29`	completed	June 7, 2026, 3:24 p.m.
NED2	Entity disambiguation (via description)	`batch_6a25985cf75081909194c11833399d37`	completed	June 7, 2026, 4:12 p.m.
PD	Predicate disambiguation	`batch_69f660f2e3708190ab658652bcfc04d0`	completed	May 2, 2026, 8:39 p.m.

Created at: April 28, 2026, 12:43 p.m.