Triple

T16170797
Position Surface form Disambiguated ID Type / Status
Subject Republic of Ezo E392428 entity
Predicate commonName P570 FINISHED
Object Ezo
Ezo was a short-lived 19th-century breakaway state in northern Japan, centered on Hokkaido and established by former Tokugawa loyalists after the Boshin War.
 E1197044 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: Ezo | Statement: [Republic of Ezo, commonName, Ezo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ezo
Context triple: [Republic of Ezo, commonName, Ezo]
  • A. Eza’r
    Eza’r is the endonym used by the Chichimeca Jonaz people for their own indigenous community and language in Mexico.
  • B. Ezha
    Ezha is a Gurage language variety spoken in Ethiopia, recognized as one of the distinct dialects within the broader Gurage linguistic group.
  • C. Eke
    Eke is a town in the Okpokwu Local Government Area of Benue State, Nigeria.
  • D. Ewohimi
    Ewohimi is a historic Esan town in Edo State, Nigeria, known for its rich cultural heritage and traditional institutions.
  • E. Echenique
    Echenique is a Spanish-language surname of Basque origin borne by various notable figures in politics, arts, and public life across the Spanish-speaking world.
  • 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: Ezo
Triple: [Republic of Ezo, commonName, Ezo]
Generated description
Ezo was a short-lived 19th-century breakaway state in northern Japan, centered on Hokkaido and established by former Tokugawa loyalists after the Boshin War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ezo
Target entity description: Ezo was a short-lived 19th-century breakaway state in northern Japan, centered on Hokkaido and established by former Tokugawa loyalists after the Boshin War.
  • A. Eza’r
    Eza’r is the endonym used by the Chichimeca Jonaz people for their own indigenous community and language in Mexico.
  • B. Ezha
    Ezha is a Gurage language variety spoken in Ethiopia, recognized as one of the distinct dialects within the broader Gurage linguistic group.
  • C. Eke
    Eke is a town in the Okpokwu Local Government Area of Benue State, Nigeria.
  • D. Ewohimi
    Ewohimi is a historic Esan town in Edo State, Nigeria, known for its rich cultural heritage and traditional institutions.
  • E. Echenique
    Echenique is a Spanish-language surname of Basque origin borne by various notable figures in politics, arts, and public life across the Spanish-speaking world.
  • 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_69d87f1d32208190942e4e499a80c18c completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21eb6de30819083af54b50ae5ae51 completed April 17, 2026, 11:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7bd87f08190a9f2a1524e5db2ba completed May 10, 2026, 3:13 a.m.
NEDg Description generation batch_69fff82b34408190ac40018f940ae370 completed May 10, 2026, 3:14 a.m.
NED2 Entity disambiguation (via description) batch_69fff8905ce48190b99f8cc3504efba2 completed May 10, 2026, 3:16 a.m.
Created at: April 10, 2026, 5:02 a.m.