Triple

T3862850
Position Surface form Disambiguated ID Type / Status
Subject Republic of Korea Army E90180 entity
Predicate shortName P43 FINISHED
Object ROKA
ROKA is the commonly used abbreviation for the Republic of Korea Army, the land warfare branch of South Korea’s armed forces.
 E395378 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: ROKA | Statement: [Republic of Korea Army, shortName, ROKA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ROKA
Context triple: [Republic of Korea Army, shortName, ROKA]
  • A. ROK
    ROK is the stock ticker symbol for Rockwell Automation, a major U.S.-based industrial automation and information technology company.
  • B. ROK
    ROK is the IATA airport code for Rockhampton Airport, a regional airport serving the city of Rockhampton in Queensland, Australia.
  • C. ROKAF
    ROKAF is the air warfare branch of South Korea’s armed forces, responsible for the country’s aerial defense and air operations.
  • D. ROKN
    ROKN is the abbreviation for the Republic of Korea Navy, the maritime branch of South Korea’s armed forces.
  • E. Byrock
    Byrock is a small rural village in north-western New South Wales, Australia, known as a remote outback stopover with historic links to the region’s pastoral and railway development.
  • 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: ROKA
Triple: [Republic of Korea Army, shortName, ROKA]
Generated description
ROKA is the commonly used abbreviation for the Republic of Korea Army, the land warfare branch of South Korea’s armed forces.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ROKA
Target entity description: ROKA is the commonly used abbreviation for the Republic of Korea Army, the land warfare branch of South Korea’s armed forces.
  • A. ROK
    ROK is the stock ticker symbol for Rockwell Automation, a major U.S.-based industrial automation and information technology company.
  • B. ROK
    ROK is the IATA airport code for Rockhampton Airport, a regional airport serving the city of Rockhampton in Queensland, Australia.
  • C. ROKAF
    ROKAF is the air warfare branch of South Korea’s armed forces, responsible for the country’s aerial defense and air operations.
  • D. ROKN
    ROKN is the abbreviation for the Republic of Korea Navy, the maritime branch of South Korea’s armed forces.
  • E. Byrock
    Byrock is a small rural village in north-western New South Wales, Australia, known as a remote outback stopover with historic links to the region’s pastoral and railway development.
  • 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_69aed95b3c088190a8f85d19e6070599 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec2417648190ad010189d304d119 completed March 9, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5123ad9188190a158721a6192cdae completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b51336c5f8819096b0b6cee47e48e3 completed March 14, 2026, 7:50 a.m.
NED2 Entity disambiguation (via description) batch_69b513b11dcc8190a2c2e3f27b4cf25e completed March 14, 2026, 7:52 a.m.
Created at: March 9, 2026, 3:19 p.m.