Triple

T11850834
Position Surface form Disambiguated ID Type / Status
Subject Republic of Korea Presidential Unit Citation E281901 entity
Predicate hasRecipientExample P98473 FINISHED
Object United States Army units in the Korean War E533600 NE FINISHED

How this triple was built (3 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: United States Army units in the Korean War | Statement: [Republic of Korea Presidential Unit Citation, hasRecipientExample, United States Army units in the Korean War]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: United States Army units in the Korean War
Context triple: [Republic of Korea Presidential Unit Citation, hasRecipientExample, United States Army units in the Korean War]
  • A. United States Army Forces in Korea
    United States Army Forces in Korea was the U.S. Army command responsible for overseeing American ground forces and military operations in Korea before the establishment of United States Forces Korea.
  • B. Korean People's Army units
    Korean People's Army units are the military formations of North Korea’s armed forces that fought against United Nations and South Korean troops during the Korean War.
  • C. Republic of Korea military units
    Republic of Korea military units are the organized armed forces formations of South Korea, encompassing its army, navy, air force, and related branches.
  • D. U.S. Army units chosen
    U.S. Army units are organized military formations of the United States Army, ranging from small tactical teams to large operational commands, structured to conduct land-based combat and support operations.
  • E. Chinese People's Volunteer Army infantry units
    The Chinese People's Volunteer Army infantry units were the ground combat forces of the People's Republic of China that fought in major engagements of the Korean War, including intense battles such as Pork Chop Hill.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasRecipientExample
Context triple: [Republic of Korea Presidential Unit Citation, hasRecipientExample, United States Army units in the Korean War]
  • A. hasRecipientRole
    Indicates that a specified entity serves as the recipient or target role in a given interaction, transaction, or relationship.
  • B. hasReceiver chosen
    Indicates that an entity serves as the recipient or target of something provided, sent, or directed by another entity.
  • C. hasRecipientWork
    Indicates that a work (such as a document, message, or creative piece) is directed or assigned to a specific recipient entity.
  • D. hasTypeOfRecipient
    Indicates that an entity is associated with a specific category or kind of recipient it is intended for or directed to.
  • E. hasRecipientQuality
    Indicates that a recipient possesses or is characterized by a particular quality or attribute.
  • F. None of above.

Provenance (4 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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a65db52c8190a218736da17d0153 completed April 10, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69f167b947d48190a07da6f5255d289a completed April 29, 2026, 2:06 a.m.
PD Predicate disambiguation batch_69d8a2573dbc8190ab432e8e28fde6cc completed April 10, 2026, 7:10 a.m.
Created at: April 8, 2026, 9:43 p.m.