Triple

T17017670
Position Surface form Disambiguated ID Type / Status
Subject 63 Building E412863 entity
Predicate owner P347 FINISHED
Object Hanwha Group E533824 NE FINISHED

How this triple was built (2 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: Hanwha Group | Statement: [63 Building, owner, Hanwha Group]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanwha Group
Context triple: [63 Building, owner, Hanwha Group]
  • A. Hanwha Group chosen
    Hanwha Group is a major South Korean conglomerate with diversified businesses spanning chemicals, energy, defense, finance, and construction.
  • B. SK Group
    SK Group is one of South Korea’s largest conglomerates, with diversified businesses spanning energy, telecommunications, semiconductors, and chemicals.
  • C. Hanwha Engineering & Construction
    Hanwha Engineering & Construction is a South Korean construction and engineering company known for undertaking large-scale international projects, including major stadiums and infrastructure developments.
  • D. POSCO Holdings
    POSCO Holdings is a South Korean multinational steelmaking and materials conglomerate that serves as the holding company of the POSCO group, one of the world’s largest steel producers.
  • E. KT Corporation
    KT Corporation is one of South Korea’s largest telecommunications companies, providing mobile, internet, and media services nationwide.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886cc4170819093deddc7b8b4b6a7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d480a58c8190a3912d26debb4311 completed April 18, 2026, 6:59 p.m.
NED1 Entity disambiguation (via context triple) batch_6a01233311648190b5f8a8e7c209d124 completed May 11, 2026, 12:30 a.m.
Created at: April 10, 2026, 5:33 a.m.