Triple

T947084
Position Surface form Disambiguated ID Type / Status
Subject Manchukuo E20436 entity
Predicate capital P234 FINISHED
Object Hsinking
Hsinking was the name given to Changchun when it served as the capital of the Japanese puppet state of Manchukuo in the early 20th century.
E111208 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: Hsinking | Statement: [Manchukuo, capital, Hsinking]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hsinking
Context triple: [Manchukuo, capital, Hsinking]
  • A. Heenvliet
    Heenvliet is a small historic town in the western Netherlands, known for its medieval castle ruins and rural setting within the province of South Holland.
  • B. Der Scutt
    Der Scutt was an American architect best known for designing prominent New York City skyscrapers, most notably Trump Tower on Fifth Avenue.
  • C. Ever Given
    Ever Given is a large container ship that gained worldwide attention in March 2021 when it became wedged in the Suez Canal, disrupting global shipping traffic.
  • D. Zułów
    Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
  • E. Aquarium
    The Aquarium at the Memphis Zoo is a dedicated exhibit showcasing a diverse collection of aquatic animals and ecosystems for education and public viewing.
  • 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: Hsinking
Triple: [Manchukuo, capital, Hsinking]
Generated description
Hsinking was the name given to Changchun when it served as the capital of the Japanese puppet state of Manchukuo in the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hsinking
Target entity description: Hsinking was the name given to Changchun when it served as the capital of the Japanese puppet state of Manchukuo in the early 20th century.
  • A. Heenvliet
    Heenvliet is a small historic town in the western Netherlands, known for its medieval castle ruins and rural setting within the province of South Holland.
  • B. Der Scutt
    Der Scutt was an American architect best known for designing prominent New York City skyscrapers, most notably Trump Tower on Fifth Avenue.
  • C. Ever Given
    Ever Given is a large container ship that gained worldwide attention in March 2021 when it became wedged in the Suez Canal, disrupting global shipping traffic.
  • D. Zułów
    Zułów is a village in present-day Lithuania best known as the birthplace of Polish statesman and military leader Józef Piłsudski.
  • E. Aquarium
    The Aquarium at the Memphis Zoo is a dedicated exhibit showcasing a diverse collection of aquatic animals and ecosystems for education and public viewing.
  • 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_69a493b0f2fc81908cd227480a5356a1 completed March 1, 2026, 7:29 p.m.
NER Named-entity recognition batch_69a4b3be19448190a8863fce3d152430 completed March 1, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69a826e7d55c8190b9b871caead76733 completed March 4, 2026, 12:34 p.m.
NEDg Description generation batch_69a845a793e08190892fe1a545095f62 completed March 4, 2026, 2:45 p.m.
NED2 Entity disambiguation (via description) batch_69a8463631608190a9ada5605e9625aa completed March 4, 2026, 2:48 p.m.
Created at: March 1, 2026, 7:40 p.m.