Triple

T17017643
Position Surface form Disambiguated ID Type / Status
Subject IFC Seoul complex E412862 entity
Predicate KoreanName P17869 FINISHED
Object IFC서울 E412862 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: IFC서울 | Statement: [IFC Seoul complex, KoreanName, IFC서울]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IFC서울
Context triple: [IFC Seoul complex, KoreanName, IFC서울]
  • A. IFC Seoul complex chosen
    IFC Seoul complex is a major mixed-use development in Seoul featuring office towers, a luxury hotel, and a large underground shopping mall.
  • B. IFC
    IFC (Industry Foundation Classes) is an open, vendor-neutral data model standard used to enable interoperability and information exchange in Building Information Modeling (BIM) across different software platforms.
  • C. IFC
    IFC (Interface Clear) is a dedicated control line in the IEEE 488 (GPIB) interface used to reset and clear connected devices on the bus.
  • D. IFC
    IFC is an American cable television channel known for airing offbeat comedies, cult films, and independent programming.
  • E. IFC Two
    IFC Two is a prominent skyscraper in Hong Kong’s International Finance Centre complex, known for its distinctive modern design and status as one of the city’s tallest buildings.
  • 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_6a012ed0b78481909a11c1529db6c1cd completed May 11, 2026, 1:20 a.m.
Created at: April 10, 2026, 5:33 a.m.