Triple

T20588760
Position Surface form Disambiguated ID Type / Status
Subject Pohang E505857 entity
Predicate knownFor P22 FINISHED
Object POSCO NE NERFINISHED

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: POSCO | Statement: [Pohang, knownFor, POSCO]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: POSCO
Context triple: [Pohang, knownFor, POSCO]
  • A. POSCO International
    POSCO International is a South Korean trading and investment company that serves as the global business arm of the POSCO Group, focusing on steel, energy, and various industrial sectors.
  • B. POSCO Holdings chosen
    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.
  • C. Hyundai Steel
    Hyundai Steel is a leading South Korean steel manufacturer and core Hyundai Motor Group affiliate known for producing a wide range of steel products for automotive, construction, and industrial uses.
  • D. Hanwha Group
    Hanwha Group is a major South Korean conglomerate with diversified businesses spanning chemicals, energy, defense, finance, and construction.
  • E. POSCO DX
    POSCO DX is a South Korean industrial digital solutions and engineering company specializing in smart factory, automation, and IT services, particularly for the steel and manufacturing sectors.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4b9669c8190b8e81fc72817d42c completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6a979e4a48190a948165fb0f3b265 completed April 20, 2026, 10:32 p.m.
Created at: April 16, 2026, 11:40 a.m.