Triple

T29778983

Position	Surface form	Disambiguated ID	Type / Status
Subject	Ye Xian	`E755456`	entity
Predicate	earliestTextualSource	`P169271`	FINISHED
Object	Youyang Zazu Youyang Zazu is a Tang dynasty Chinese miscellany that preserves a wide range of anecdotes, folklore, and early literary tales, including one of the earliest known versions of the Cinderella story.	`E1883570`	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: Youyang Zazu | Statement: [Ye Xian, earliestTextualSource, Youyang Zazu]

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: Youyang Zazu
Triple: [Ye Xian, earliestTextualSource, Youyang Zazu]

Generated description

Youyang Zazu is a Tang dynasty Chinese miscellany that preserves a wide range of anecdotes, folklore, and early literary tales, including one of the earliest known versions of the Cinderella story.

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

Target predicate: earliestTextualSource
Context triple: [Ye Xian, earliestTextualSource, Youyang Zazu]

A. earliestTextsIn
Indicates that certain texts are among the earliest known examples found in or associated with a particular place or context.
B. earliestFullSource chosen
Indicates that one entity is the earliest (in time or order) complete source or origin for another entity.
C. earliestManuscripts
Indicates that the related entity (e.g., a text or work) is associated with its earliest known surviving manuscripts or documentary witnesses.
D. earliestKnownPeriod
Indicates the earliest historical or temporal period in which the subject is known or documented to have existed, occurred, or been relevant.
E. earliestCompilationAttributedTo
Indicates that one entity is regarded as the earliest known or first compilation associated with, or attributed to, another entity.
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_69f0ef878574819088c867fd1a5c8b86`	completed	April 28, 2026, 5:33 p.m.
NER	Named-entity recognition	`batch_69f6f8565134819096aac0175f924a9f`	completed	May 3, 2026, 7:25 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a26c8fdfe048190b0f35f80c49a1e05`	completed	June 8, 2026, 1:51 p.m.
NEDg	Description generation	`batch_6a26cce42b208190b30d28fe1e55105b`	completed	June 8, 2026, 2:08 p.m.
NED2	Entity disambiguation (via description)	`batch_6a26d421b5408190bfb77e624443fad8`	completed	June 8, 2026, 2:39 p.m.
PD	Predicate disambiguation	`batch_69f6f65fd1d08190b88e5e68ba268500`	completed	May 3, 2026, 7:16 a.m.

Created at: April 28, 2026, 8:48 p.m.