Triple

T5180642
Position Surface form Disambiguated ID Type / Status
Subject Offutt Air Force Base E116910 entity
Predicate hasICAOCode P419 FINISHED
Object KOFF
KOFF is the ICAO airport code for Offutt Air Force Base, a major United States Air Force installation near Omaha, Nebraska.
 E499701 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: KOFF | Statement: [Offutt Air Force Base, hasICAOCode, KOFF]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KOFF
Context triple: [Offutt Air Force Base, hasICAOCode, KOFF]
  • A. COFHE
    COFHE is a consortium of highly selective private colleges and universities in the United States that collaborates on issues of financial aid, admissions, and institutional research.
  • B. Mr. Coffee
    Mr. Coffee is a popular American brand best known for its automatic drip coffee makers and related coffee appliances for home use.
  • C. Caffe
    Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
  • D. Coffee-Mate
    Coffee-Mate is a popular non-dairy coffee creamer brand known for its wide variety of flavored and powdered creamers used to enhance coffee.
  • E. COFF
    COFF (Common Object File Format) is a standard file format used primarily on Unix-like and Windows systems for object code, executables, and shared libraries.
  • 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: KOFF
Triple: [Offutt Air Force Base, hasICAOCode, KOFF]
Generated description
KOFF is the ICAO airport code for Offutt Air Force Base, a major United States Air Force installation near Omaha, Nebraska.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KOFF
Target entity description: KOFF is the ICAO airport code for Offutt Air Force Base, a major United States Air Force installation near Omaha, Nebraska.
  • A. COFHE
    COFHE is a consortium of highly selective private colleges and universities in the United States that collaborates on issues of financial aid, admissions, and institutional research.
  • B. Mr. Coffee
    Mr. Coffee is a popular American brand best known for its automatic drip coffee makers and related coffee appliances for home use.
  • C. Caffe
    Caffe is an open-source deep learning framework known for its speed and modular design, widely used in computer vision research and applications.
  • D. Coffee-Mate
    Coffee-Mate is a popular non-dairy coffee creamer brand known for its wide variety of flavored and powdered creamers used to enhance coffee.
  • E. COFF
    COFF (Common Object File Format) is a standard file format used primarily on Unix-like and Windows systems for object code, executables, and shared libraries.
  • 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_69bd446140f08190becb93c61158f27f completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd799a322c8190b8a590cfe70761f5 completed March 20, 2026, 4:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69bed959004c81908e28156aae15bee6 completed March 21, 2026, 5:46 p.m.
NEDg Description generation batch_69beda0419108190862d028a14227e8a completed March 21, 2026, 5:48 p.m.
NED2 Entity disambiguation (via description) batch_69bedaa232ac81908c5ee2d4ba8cbcd7 completed March 21, 2026, 5:51 p.m.
Created at: March 20, 2026, 1:45 p.m.