Triple

T20588793
Position Surface form Disambiguated ID Type / Status
Subject Pohang E505857 entity
Predicate hasLandmark P105 FINISHED
Object Jukdo Market 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: Jukdo Market | Statement: [Pohang, hasLandmark, Jukdo Market]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jukdo Market
Context triple: [Pohang, hasLandmark, Jukdo Market]
  • A. Jukdo Market chosen
    Jukdo Market is a large traditional marketplace in Pohang, South Korea, known for its fresh seafood, local produce, and bustling street food stalls.
  • B. Bupyeong Market
    Bupyeong Market is a large traditional marketplace in Incheon, South Korea, known for its extensive underground shopping area, street food, and variety of goods.
  • C. Gukje Market
    Gukje Market is one of Busan’s largest and oldest traditional markets, known for its maze-like alleys packed with stalls selling food, clothing, and household goods.
  • D. Bupyeong Kkangtong Market
    Bupyeong Kkangtong Market is a famous traditional market in Busan, South Korea, known for its bustling night market atmosphere, diverse street food, and variety of local goods.
  • E. Gijang Market
    Gijang Market is a traditional coastal seafood market in Gijang County, South Korea, known for its fresh marine products and local specialties.
  • 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.