Triple

T15901143
Position Surface form Disambiguated ID Type / Status
Subject Battle of Toba–Fushimi E385590 entity
Predicate location P40 FINISHED
Object Yodo
Yodo is a district in Kyoto, Japan, historically notable as a key strategic site during the late Edo period, including the Battle of Toba–Fushimi.
E1213611 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: Yodo | Statement: [Battle of Toba–Fushimi, location, Yodo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yodo
Context triple: [Battle of Toba–Fushimi, location, Yodo]
  • A. Ogawa
    Ogawa is a town in Saitama Prefecture, Japan, known for its traditional Japanese paper (washi) production and its role as a local transport hub.
  • B. Ogawa
    Ogawa is a serotype of the bacterium Vibrio cholerae O1, commonly associated with cholera outbreaks worldwide.
  • C. Chikuma
    Chikuma was a Japanese Imperial Navy heavy cruiser that served prominently in World War II, including major Pacific naval battles.
  • D. Yabun
    Yabun is a major annual Aboriginal and Torres Strait Islander cultural festival held in Sydney, celebrating Indigenous music, dance, and community.
  • E. Taihe
    Taihe was a historical Chinese era name used during the Three Kingdoms period under the state of Cao Wei.
  • 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: Yodo
Triple: [Battle of Toba–Fushimi, location, Yodo]
Generated description
Yodo is a district in Kyoto, Japan, historically notable as a key strategic site during the late Edo period, including the Battle of Toba–Fushimi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yodo
Target entity description: Yodo is a district in Kyoto, Japan, historically notable as a key strategic site during the late Edo period, including the Battle of Toba–Fushimi.
  • A. Ogawa
    Ogawa is a town in Saitama Prefecture, Japan, known for its traditional Japanese paper (washi) production and its role as a local transport hub.
  • B. Ogawa
    Ogawa is a serotype of the bacterium Vibrio cholerae O1, commonly associated with cholera outbreaks worldwide.
  • C. Chikuma
    Chikuma was a Japanese Imperial Navy heavy cruiser that served prominently in World War II, including major Pacific naval battles.
  • D. Yabun
    Yabun is a major annual Aboriginal and Torres Strait Islander cultural festival held in Sydney, celebrating Indigenous music, dance, and community.
  • E. Taihe
    Taihe was a historical Chinese era name used during the Three Kingdoms period under the state of Cao Wei.
  • 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_69d86da5b800819083a31be937d738b0 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1563db01081908dd94a2536ef2107 completed April 16, 2026, 9:35 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00456b590c8190949fd23cb5cec1e8 completed May 10, 2026, 8:44 a.m.
NEDg Description generation batch_6a004771e5108190a7fd4f6e274e455a completed May 10, 2026, 8:53 a.m.
NED2 Entity disambiguation (via description) batch_6a00482646c88190a8e3a5299146b504 completed May 10, 2026, 8:56 a.m.
Created at: April 10, 2026, 4:51 a.m.