Triple

T1104581
Position Surface form Disambiguated ID Type / Status
Subject Wushe Incident E25457 entity
Predicate location P40 FINISHED
Object Wushe
Wushe is a mountainous region in central Taiwan historically inhabited by Indigenous Seediq people and known as the site of the 1930 Wushe Incident.
 E132886 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: Wushe | Statement: [Wushe Incident, location, Wushe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wushe
Context triple: [Wushe Incident, location, Wushe]
  • A. Lu’an
    Lu’an is a prefecture-level city in western Anhui Province, China, known for its mountainous terrain, tea production, and historical sites.
  • B. Katchal
    Katchal is a dialect of the Nicobarese language spoken by the indigenous community on Katchal Island in India’s Nicobar Islands.
  • C. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • D. Sehore
    Sehore is a town and district headquarters in central India, located near the state capital Bhopal in Madhya Pradesh.
  • E. Dehu
    Dehu is a pilgrimage town in Maharashtra, India, revered as the birthplace and spiritual center of the 17th-century Marathi saint-poet Tukaram.
  • 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: Wushe
Triple: [Wushe Incident, location, Wushe]
Generated description
Wushe is a mountainous region in central Taiwan historically inhabited by Indigenous Seediq people and known as the site of the 1930 Wushe Incident.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wushe
Target entity description: Wushe is a mountainous region in central Taiwan historically inhabited by Indigenous Seediq people and known as the site of the 1930 Wushe Incident.
  • A. Lu’an
    Lu’an is a prefecture-level city in western Anhui Province, China, known for its mountainous terrain, tea production, and historical sites.
  • B. Katchal
    Katchal is a dialect of the Nicobarese language spoken by the indigenous community on Katchal Island in India’s Nicobar Islands.
  • C. Southesk
    Southesk is the traditional war cry associated with Clan Carnegie, a Scottish noble family from Angus.
  • D. Sehore
    Sehore is a town and district headquarters in central India, located near the state capital Bhopal in Madhya Pradesh.
  • E. Dehu
    Dehu is a pilgrimage town in Maharashtra, India, revered as the birthplace and spiritual center of the 17th-century Marathi saint-poet Tukaram.
  • 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_69a49428d4448190b3b36991ceae87ce completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b9e1047481909af1cf8df2a01fff completed March 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac66293b5c819091eb69db328d5698 completed March 7, 2026, 5:53 p.m.
NEDg Description generation batch_69ac671c11f48190afeebfe76544ef70 completed March 7, 2026, 5:57 p.m.
NED2 Entity disambiguation (via description) batch_69ac6787d5908190b154ff700227d282 completed March 7, 2026, 5:59 p.m.
Created at: March 1, 2026, 7:43 p.m.