Triple

T8487113
Position Surface form Disambiguated ID Type / Status
Subject Levanga Hokkaido E200857 entity
Predicate shortName P43 FINISHED
Object Levanga
Levanga is a professional basketball team based in Hokkaido, Japan, competing in the country’s top-tier B.League.
 E736192 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: Levanga | Statement: [Levanga Hokkaido, shortName, Levanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Levanga
Context triple: [Levanga Hokkaido, shortName, Levanga]
  • A. Loenga
    Loenga is a small residential and industrial neighborhood in Oslo, Norway, situated near the railway yards and the Oslofjord.
  • B. Lugana
    Lugana is an Italian white wine appellation near Lake Garda, renowned for its fresh, mineral-driven wines primarily made from the Turbiana grape.
  • C. Lopevi
    Lopevi is an Oceanic language of Vanuatu, traditionally spoken on Lopevi Island in the central part of the archipelago.
  • D. Lugensa
    Lugensa is a genus of seabirds in the petrel family Procellariidae, comprising medium-sized, oceanic birds adapted to long-distance flight over open waters.
  • E. Kalanga
    Kalanga is a Southern Bantu language spoken primarily in southwestern Zimbabwe and northeastern Botswana by the Kalanga people.
  • 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: Levanga
Triple: [Levanga Hokkaido, shortName, Levanga]
Generated description
Levanga is a professional basketball team based in Hokkaido, Japan, competing in the country’s top-tier B.League.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Levanga
Target entity description: Levanga is a professional basketball team based in Hokkaido, Japan, competing in the country’s top-tier B.League.
  • A. Loenga
    Loenga is a small residential and industrial neighborhood in Oslo, Norway, situated near the railway yards and the Oslofjord.
  • B. Lugana
    Lugana is an Italian white wine appellation near Lake Garda, renowned for its fresh, mineral-driven wines primarily made from the Turbiana grape.
  • C. Lopevi
    Lopevi is an Oceanic language of Vanuatu, traditionally spoken on Lopevi Island in the central part of the archipelago.
  • D. Lugensa
    Lugensa is a genus of seabirds in the petrel family Procellariidae, comprising medium-sized, oceanic birds adapted to long-distance flight over open waters.
  • E. Kalanga
    Kalanga is a Southern Bantu language spoken primarily in southwestern Zimbabwe and northeastern Botswana by the Kalanga people.
  • 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_69ca831d7b148190a6e32c1de43ab13b completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe53c4d608190a766c0e919a4b96f completed March 31, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce3a45e30c8190838ac499bbc66fbd completed April 2, 2026, 9:43 a.m.
NEDg Description generation batch_69ce3c22f3c0819084803630d438c55e completed April 2, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69ce3ca57ec081909a14d962eee2c9a5 completed April 2, 2026, 9:53 a.m.
Created at: March 30, 2026, 6:13 p.m.