Triple

T16349210
Position Surface form Disambiguated ID Type / Status
Subject Marine Corps Air Station Beaufort E397013 entity
Predicate ICAOCode P419 FINISHED
Object KNBC
KNBC is the ICAO airport code for Marine Corps Air Station Beaufort, a major United States Marine Corps aviation facility in South Carolina.
 E1209102 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: KNBC | Statement: [Marine Corps Air Station Beaufort, ICAOCode, KNBC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KNBC
Context triple: [Marine Corps Air Station Beaufort, ICAOCode, KNBC]
  • A. KNBC-TV
    KNBC-TV is the NBC-owned and operated television station serving the Los Angeles, California market.
  • B. KNTV
    KNTV is a television station serving the San Francisco Bay Area, operating as the local NBC owned-and-operated affiliate.
  • C. KXAN-TV
    KXAN-TV is a television station serving the Austin, Texas market, known primarily as the local NBC affiliate.
  • D. KTTV
    KTTV is a Los Angeles-based television station, historically known as a major outlet for sports broadcasting and local news coverage.
  • E. KABC-TV
    KABC-TV is a major ABC-owned television station serving the Los Angeles, California media market.
  • 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: KNBC
Triple: [Marine Corps Air Station Beaufort, ICAOCode, KNBC]
Generated description
KNBC is the ICAO airport code for Marine Corps Air Station Beaufort, a major United States Marine Corps aviation facility in South Carolina.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KNBC
Target entity description: KNBC is the ICAO airport code for Marine Corps Air Station Beaufort, a major United States Marine Corps aviation facility in South Carolina.
  • A. KNBC-TV
    KNBC-TV is the NBC-owned and operated television station serving the Los Angeles, California market.
  • B. KNTV
    KNTV is a television station serving the San Francisco Bay Area, operating as the local NBC owned-and-operated affiliate.
  • C. KXAN-TV
    KXAN-TV is a television station serving the Austin, Texas market, known primarily as the local NBC affiliate.
  • D. KTTV
    KTTV is a Los Angeles-based television station, historically known as a major outlet for sports broadcasting and local news coverage.
  • E. KABC-TV
    KABC-TV is a major ABC-owned television station serving the Los Angeles, California media market.
  • 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_69d87f26864c819088365ca381a003c2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2da120ec081909bbf32bd128b2e01 completed April 18, 2026, 1:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002db40e0481908d919f2285e48a23 completed May 10, 2026, 7:03 a.m.
NEDg Description generation batch_6a003082f0008190aeae2fbbfc3a8acf completed May 10, 2026, 7:15 a.m.
NED2 Entity disambiguation (via description) batch_6a00312a4fc48190b6bd6ad9db71bb4d completed May 10, 2026, 7:18 a.m.
Created at: April 10, 2026, 5:07 a.m.