Triple

T6940405
Position Surface form Disambiguated ID Type / Status
Subject Khmer National Armed Forces E160658 entity
Predicate abbreviation P43 FINISHED
Object FANK
FANK was the acronym for the Khmer National Armed Forces, the military of the pro-U.S. Lon Nol government in Cambodia during the Cambodian Civil War.
 E628701 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: FANK | Statement: [Khmer National Armed Forces, abbreviation, FANK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: FANK
Context triple: [Khmer National Armed Forces, abbreviation, FANK]
  • A. Frank-N-Dank
    Frank-N-Dank is a Detroit hip hop duo known for their close collaboration with producer J Dilla and their raw, energetic underground rap style.
  • B. Funka
    Funka is a small village in northern Poland known for its scenic lakeside setting and recreational access to Lake Charzykowskie.
  • C. Fu
    Fu is a Chinese surname borne by various notable historical and contemporary figures across politics, arts, and other fields.
  • D. F.A.C.
    F.A.C. is the standard legal abbreviation used to refer to the Florida Administrative Code, which contains the administrative rules and regulations of the state of Florida.
  • E. FAB
    FAB is the acronym for the Brazilian Air Force, the aerial warfare branch of Brazil’s armed forces.
  • 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: FANK
Triple: [Khmer National Armed Forces, abbreviation, FANK]
Generated description
FANK was the acronym for the Khmer National Armed Forces, the military of the pro-U.S. Lon Nol government in Cambodia during the Cambodian Civil War.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: FANK
Target entity description: FANK was the acronym for the Khmer National Armed Forces, the military of the pro-U.S. Lon Nol government in Cambodia during the Cambodian Civil War.
  • A. Frank-N-Dank
    Frank-N-Dank is a Detroit hip hop duo known for their close collaboration with producer J Dilla and their raw, energetic underground rap style.
  • B. Funka
    Funka is a small village in northern Poland known for its scenic lakeside setting and recreational access to Lake Charzykowskie.
  • C. Fu
    Fu is a Chinese surname borne by various notable historical and contemporary figures across politics, arts, and other fields.
  • D. F.A.C.
    F.A.C. is the standard legal abbreviation used to refer to the Florida Administrative Code, which contains the administrative rules and regulations of the state of Florida.
  • E. FAB
    FAB is the acronym for the Brazilian Air Force, the aerial warfare branch of Brazil’s armed forces.
  • 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_69c6884f3db4819080ad65da69386206 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6da641ce08190a133c9ba4977755d completed March 27, 2026, 7:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7515880948190970cadd7adeda435 completed March 28, 2026, 3:56 a.m.
NEDg Description generation batch_69c7524e3ef48190a78601ca290f133d completed March 28, 2026, 4 a.m.
NED2 Entity disambiguation (via description) batch_69c752dca6e08190a087898d99c015ac completed March 28, 2026, 4:02 a.m.
Created at: March 27, 2026, 2:28 p.m.