Triple

T14372134
Position Surface form Disambiguated ID Type / Status
Subject Geoje E356381 entity
Predicate hasSettlement P1068 FINISHED
Object Okpo
Okpo is a coastal town on Geoje Island in South Korea, known for its major shipbuilding industry and proximity to the Daewoo Shipbuilding & Marine Engineering shipyard.
 E1095378 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: Okpo | Statement: [Geoje, hasSettlement, Okpo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Okpo
Context triple: [Geoje, hasSettlement, Okpo]
  • A. Okobo
    Okobo are a subgroup of the Oron people of southeastern Nigeria, known for their distinct language, cultural practices, and coastal riverine settlements in Akwa Ibom State.
  • B. Okeke
    Okeke is a common Igbo surname of Nigerian origin, borne by many individuals across various professions and regions.
  • C. Opoji
    Opoji is a town and traditional community within the Esan ethnic area of Edo State, Nigeria, known for its indigenous customs and local governance structures.
  • D. Okak
    Okak is a dialectal variety of the Fang language spoken by Fang communities in Central Africa.
  • E. Okonedo
    Okonedo is the surname of Sophie Okonedo, a British actress known for her acclaimed performances in film, television, and theatre.
  • 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: Okpo
Triple: [Geoje, hasSettlement, Okpo]
Generated description
Okpo is a coastal town on Geoje Island in South Korea, known for its major shipbuilding industry and proximity to the Daewoo Shipbuilding & Marine Engineering shipyard.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Okpo
Target entity description: Okpo is a coastal town on Geoje Island in South Korea, known for its major shipbuilding industry and proximity to the Daewoo Shipbuilding & Marine Engineering shipyard.
  • A. Okobo
    Okobo are a subgroup of the Oron people of southeastern Nigeria, known for their distinct language, cultural practices, and coastal riverine settlements in Akwa Ibom State.
  • B. Okeke
    Okeke is a common Igbo surname of Nigerian origin, borne by many individuals across various professions and regions.
  • C. Opoji
    Opoji is a town and traditional community within the Esan ethnic area of Edo State, Nigeria, known for its indigenous customs and local governance structures.
  • D. Okak
    Okak is a dialectal variety of the Fang language spoken by Fang communities in Central Africa.
  • E. Okonedo
    Okonedo is the surname of Sophie Okonedo, a British actress known for her acclaimed performances in film, television, and theatre.
  • 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_69d8279163a081908aec45c0e3f1e02f completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8fb2082c8190b42cc5f2bab4f574 completed April 14, 2026, 7:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd4c5363a081909681b54c1d8218dc completed May 8, 2026, 2:37 a.m.
NEDg Description generation batch_69fd4e795948819097c43e30902f1654 completed May 8, 2026, 2:46 a.m.
NED2 Entity disambiguation (via description) batch_69fd4f04d7ec819095b64d4811440166 completed May 8, 2026, 2:48 a.m.
Created at: April 10, 2026, 1:15 a.m.