Triple

T1629446
Position Surface form Disambiguated ID Type / Status
Subject Cantonese opera E35223 entity
Predicate hasRoleType P5518 FINISHED
Object huadan
Huadan is a lively young female role type in traditional Chinese opera, especially known for portraying spirited maidens and clever heroines.
 E185264 NE FINISHED

How this triple was built (4 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: huadan | Statement: [Cantonese opera, hasRoleType, huadan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: huadan
Context triple: [Cantonese opera, hasRoleType, huadan]
  • A. harae
    Harae is a central Shinto purification ritual intended to cleanse spiritual impurity and restore harmony between people, nature, and the kami.
  • B. Handai
    Handai is the common Japanese abbreviation for Osaka University, a leading national research university based in Osaka, Japan.
  • C. HU
    HU is the postcode area covering Kingston upon Hull and its surrounding region in the United Kingdom.
  • D. HAD
    HAD is the commonly used abbreviation for the Historical Astronomy Division, a group focused on the study and promotion of the history of astronomy.
  • E. Hakka
    Hakka is a Sinitic language spoken primarily by the Hakka people across southern China and various overseas Chinese communities.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: huadan
Triple: [Cantonese opera, hasRoleType, huadan]
Generated description
Huadan is a lively young female role type in traditional Chinese opera, especially known for portraying spirited maidens and clever heroines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: huadan
Target entity description: Huadan is a lively young female role type in traditional Chinese opera, especially known for portraying spirited maidens and clever heroines.
  • A. harae
    Harae is a central Shinto purification ritual intended to cleanse spiritual impurity and restore harmony between people, nature, and the kami.
  • B. Handai
    Handai is the common Japanese abbreviation for Osaka University, a leading national research university based in Osaka, Japan.
  • C. HU
    HU is the postcode area covering Kingston upon Hull and its surrounding region in the United Kingdom.
  • D. HAD
    HAD is the commonly used abbreviation for the Historical Astronomy Division, a group focused on the study and promotion of the history of astronomy.
  • E. Hakka
    Hakka is a Sinitic language spoken primarily by the Hakka people across southern China and various overseas Chinese communities.
  • F. None of above. chosen

Provenance (5 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_69a886036bc081909ff5de16dbe5e8ea completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb3a9b634819086b44f1574e97dcb completed March 7, 2026, 5:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad58d5acd8819090c51678ce0f63f0 completed March 8, 2026, 11:09 a.m.
NEDg Description generation batch_69ad5a619da481908d66837ea94c91cf completed March 8, 2026, 11:15 a.m.
NED2 Entity disambiguation (via description) batch_69ad5b41a68c8190ba293d8e8c35521b completed March 8, 2026, 11:19 a.m.
Created at: March 4, 2026, 7:28 p.m.