Triple

T16924203
Position Surface form Disambiguated ID Type / Status
Subject Chinese First Phase Offensive E410523 entity
Predicate location P40 FINISHED
Object Unsan
Unsan is a town in North Korea notable for being a key battleground during the early stages of the Korean War.
E1241064 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: Unsan | Statement: [Chinese First Phase Offensive, location, Unsan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unsan
Context triple: [Chinese First Phase Offensive, location, Unsan]
  • A. Ukaan
    Ukaan is a little-documented Niger-Congo language spoken by a small community in southwestern Nigeria.
  • B. Unrug
    Unrug is a Polish noble surname most notably associated with Józef Unrug, a distinguished Polish Navy admiral and World War II commander.
  • C. Naju
    Naju is a historic city in South Korea known for its pear cultivation and location in the southwestern province of South Jeolla.
  • D. Ususan
    Ususan is a barangay (village-level administrative division) located within the city of Taguig in Metro Manila, Philippines.
  • E. Sa’och
    Sa’och is an indigenous Pearic language (and its associated ethnic group) of mainland Southeast Asia, traditionally spoken by a small community in Cambodia and nearby regions.
  • 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: Unsan
Triple: [Chinese First Phase Offensive, location, Unsan]
Generated description
Unsan is a town in North Korea notable for being a key battleground during the early stages of the Korean War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Unsan
Target entity description: Unsan is a town in North Korea notable for being a key battleground during the early stages of the Korean War.
  • A. Ukaan
    Ukaan is a little-documented Niger-Congo language spoken by a small community in southwestern Nigeria.
  • B. Unrug
    Unrug is a Polish noble surname most notably associated with Józef Unrug, a distinguished Polish Navy admiral and World War II commander.
  • C. Naju
    Naju is a historic city in South Korea known for its pear cultivation and location in the southwestern province of South Jeolla.
  • D. Ususan
    Ususan is a barangay (village-level administrative division) located within the city of Taguig in Metro Manila, Philippines.
  • E. Sa’och
    Sa’och is an indigenous Pearic language (and its associated ethnic group) of mainland Southeast Asia, traditionally spoken by a small community in Cambodia and nearby regions.
  • 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_69d886c7b1e481908c3766dfa8c13458 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3cdf1347c819085cf754a0c3e19ed completed April 18, 2026, 6:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00cfd8a88c8190adda386b62fe543c completed May 10, 2026, 6:35 p.m.
NEDg Description generation batch_6a00d0a0852c8190991af93d50fa2216 completed May 10, 2026, 6:38 p.m.
NED2 Entity disambiguation (via description) batch_6a00d14d13548190bb09408d28ff1ef8 completed May 10, 2026, 6:41 p.m.
Created at: April 10, 2026, 5:30 a.m.