Triple

T21362048
Position Surface form Disambiguated ID Type / Status
Subject Tsukuba E526806 entity
Predicate precededBy P97 FINISHED
Object Oho
Oho is a former municipality in Ibaraki Prefecture, Japan, that was merged into the city of Tsukuba.
 E1480181 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: Oho | Statement: [Tsukuba, precededBy, Oho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Oho
Context triple: [Tsukuba, precededBy, Oho]
  • A. Wikana
    Wikana was an Indonesian nationalist and youth leader who played a key role in pressuring Sukarno and Hatta to proclaim Indonesia’s independence during the Japanese occupation.
  • B. Gosiute
    Gosiute is a dialect of the Shoshoni language traditionally spoken by the Goshute people of the Great Basin region in the western United States.
  • C. Βίτσι
    Βίτσι is a mountain in northern Greece known for its natural beauty, forests, and role in modern Greek history.
  • D. Ohnice
    Ohnice is a poetry collection by Czech poet Jiří Orten, reflecting his introspective and emotionally charged lyrical style.
  • E. Kanajo
    Kanajo is a character or entity presented as the counterpart or parallel version of Manajo, typically within the same fictional or conceptual setting.
  • 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: Oho
Triple: [Tsukuba, precededBy, Oho]
Generated description
Oho is a former municipality in Ibaraki Prefecture, Japan, that was merged into the city of Tsukuba.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Oho
Target entity description: Oho is a former municipality in Ibaraki Prefecture, Japan, that was merged into the city of Tsukuba.
  • A. Wikana
    Wikana was an Indonesian nationalist and youth leader who played a key role in pressuring Sukarno and Hatta to proclaim Indonesia’s independence during the Japanese occupation.
  • B. Gosiute
    Gosiute is a dialect of the Shoshoni language traditionally spoken by the Goshute people of the Great Basin region in the western United States.
  • C. Βίτσι
    Βίτσι is a mountain in northern Greece known for its natural beauty, forests, and role in modern Greek history.
  • D. Ohnice
    Ohnice is a poetry collection by Czech poet Jiří Orten, reflecting his introspective and emotionally charged lyrical style.
  • E. Kanajo
    Kanajo is a character or entity presented as the counterpart or parallel version of Manajo, typically within the same fictional or conceptual setting.
  • 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_69e0b51d8a308190b09113b3b3f9bc15 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8b06b219c81908f7674ae459e7931 completed April 22, 2026, 11:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09ad69993881909b52927f7372fa0a completed May 17, 2026, 11:58 a.m.
NEDg Description generation batch_6a09ae3744588190877e88dd38a80ebd completed May 17, 2026, 12:01 p.m.
NED2 Entity disambiguation (via description) batch_6a09af2184808190b42b5073e90bd83d completed May 17, 2026, 12:05 p.m.
Created at: April 16, 2026, 5:08 p.m.