Triple

T11519585
Position Surface form Disambiguated ID Type / Status
Subject Yayoi period E273125 entity
Predicate archaeologicalEvidence P3650 FINISHED
Object Toro site
Toro site is a significant Japanese archaeological site in Shizuoka Prefecture known for its well-preserved remains of a Yayoi-period agricultural settlement, including paddy fields and dwellings.
E929937 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: Toro site | Statement: [Yayoi period, archaeologicalEvidence, Toro site]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Toro site
Context triple: [Yayoi period, archaeologicalEvidence, Toro site]
  • A. Sito
    Sito is an epithet of the Greek goddess Demeter that emphasizes her role as the provider of grain and sustenance.
  • B. Toro
    Toro is a Marvel Comics supervillain and member of the Invaders, often depicted as a powerful, bull-like adversary.
  • C. Toro
    Toro is the official bull-themed mascot of the NFL's Houston Texans, known for entertaining fans at games and team events.
  • D. Toro
    Toro is a historic town in the province of Zamora, Castile and León, Spain, known for its medieval architecture and wine production.
  • E. Toro
    Toro is the traditional nickname of Torino F.C., a historic Italian football club based in Turin.
  • 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: Toro site
Triple: [Yayoi period, archaeologicalEvidence, Toro site]
Generated description
Toro site is a significant Japanese archaeological site in Shizuoka Prefecture known for its well-preserved remains of a Yayoi-period agricultural settlement, including paddy fields and dwellings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Toro site
Target entity description: Toro site is a significant Japanese archaeological site in Shizuoka Prefecture known for its well-preserved remains of a Yayoi-period agricultural settlement, including paddy fields and dwellings.
  • A. Sito
    Sito is an epithet of the Greek goddess Demeter that emphasizes her role as the provider of grain and sustenance.
  • B. Toro
    Toro is a Marvel Comics supervillain and member of the Invaders, often depicted as a powerful, bull-like adversary.
  • C. Toro
    Toro is the official bull-themed mascot of the NFL's Houston Texans, known for entertaining fans at games and team events.
  • D. Toro
    Toro is the traditional nickname of Torino F.C., a historic Italian football club based in Turin.
  • E. Toro
    Toro is a traditional kingdom and region in western Uganda, known for its rich cultural heritage and historical monarchy.
  • 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_69d6aae2c3748190bed2ea50dfb160dc completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d87fcf927081908ef89eff7ad833b0 completed April 10, 2026, 4:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69e62540ff4c81909206db0344842c3b completed April 20, 2026, 1:08 p.m.
NEDg Description generation batch_69e62cf5b9988190bc1935993f0111f7 completed April 20, 2026, 1:41 p.m.
NED2 Entity disambiguation (via description) batch_69e66433ddb48190994bb1160b0ff732 completed April 20, 2026, 5:36 p.m.
Created at: April 8, 2026, 9:36 p.m.