Triple

T17900043
Position Surface form Disambiguated ID Type / Status
Subject Okayama Prefecture E447546 entity
Predicate hasCity P316 FINISHED
Object Soja
Soja is a small city in western Japan’s Okayama Prefecture known for its historic sites and rural landscapes.
 E1295610 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: Soja | Statement: [Okayama Prefecture, hasCity, Soja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Soja
Context triple: [Okayama Prefecture, hasCity, Soja]
  • A. SOJA
    SOJA (Soldiers of Jah Army) is an American reggae band known for blending roots reggae with rock and dub influences and for their socially conscious lyrics.
  • B. Soya
    Soya was a Soviet aircraft carrier originally built for the Soviet Navy and later renamed from Varyag before entering service.
  • C. Soya
    Soya was the Japanese name given to the captured Russian protected cruiser Varyag after it was incorporated into the Imperial Japanese Navy.
  • D. Glycine soja
    Glycine soja is the wild ancestor of cultivated soybean, a leguminous plant native to East Asia known for its genetic diversity and importance in soybean breeding and research.
  • E. Glycine max
    Glycine max is the cultivated soybean plant, a major legume crop grown worldwide for its protein- and oil-rich seeds used in food, feed, and industrial products.
  • 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: Soja
Triple: [Okayama Prefecture, hasCity, Soja]
Generated description
Soja is a small city in western Japan’s Okayama Prefecture known for its historic sites and rural landscapes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Soja
Target entity description: Soja is a small city in western Japan’s Okayama Prefecture known for its historic sites and rural landscapes.
  • A. SOJA
    SOJA (Soldiers of Jah Army) is an American reggae band known for blending roots reggae with rock and dub influences and for their socially conscious lyrics.
  • B. Soya
    Soya was a Soviet aircraft carrier originally built for the Soviet Navy and later renamed from Varyag before entering service.
  • C. Soya
    Soya was the Japanese name given to the captured Russian protected cruiser Varyag after it was incorporated into the Imperial Japanese Navy.
  • D. Glycine soja
    Glycine soja is the wild ancestor of cultivated soybean, a leguminous plant native to East Asia known for its genetic diversity and importance in soybean breeding and research.
  • E. Glycine max
    Glycine max is the cultivated soybean plant, a major legume crop grown worldwide for its protein- and oil-rich seeds used in food, feed, and industrial products.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d8321bc8190a3f679d96323cbbb completed April 19, 2026, 9:16 a.m.
NED1 Entity disambiguation (via context triple) batch_6a031b286b088190b6cf9731da839669 completed May 12, 2026, 12:20 p.m.
NEDg Description generation batch_6a031c3658988190b59fa17d616cad9b completed May 12, 2026, 12:25 p.m.
NED2 Entity disambiguation (via description) batch_6a031c9914dc819099da3b2174a5fbc7 completed May 12, 2026, 12:27 p.m.
Created at: April 10, 2026, 10:19 a.m.