Triple

T16061461
Position Surface form Disambiguated ID Type / Status
Subject Beijing Nanyuan Airport E389622 entity
Predicate ICAOcode P419 FINISHED
Object ZBNY
ZBNY is the ICAO airport code for Beijing Nanyuan Airport, the former military-civilian airport that once served as a secondary airport for Beijing, China.
E1191142 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: ZBNY | Statement: [Beijing Nanyuan Airport, ICAOcode, ZBNY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ZBNY
Context triple: [Beijing Nanyuan Airport, ICAOcode, ZBNY]
  • A. BZN
    BZN is a Dutch pop band best known for its melodic, easy-listening songs and long-standing popularity in the Netherlands.
  • B. ZBYN
    ZBYN is the ICAO airport code for Taiyuan Wusu International Airport in Taiyuan, Shanxi Province, China.
  • C. BYN
    BYN is the ISO 4217 currency code for the current Belarusian ruble, the official currency of Belarus.
  • D. BBNZ
    BBNZ is the national governing body responsible for overseeing and developing the sport of basketball in New Zealand.
  • E. NYJ
    NYJ is the common abbreviation for the New York Jets, a professional American football team based in the New York metropolitan area that competes in the NFL.
  • 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: ZBNY
Triple: [Beijing Nanyuan Airport, ICAOcode, ZBNY]
Generated description
ZBNY is the ICAO airport code for Beijing Nanyuan Airport, the former military-civilian airport that once served as a secondary airport for Beijing, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ZBNY
Target entity description: ZBNY is the ICAO airport code for Beijing Nanyuan Airport, the former military-civilian airport that once served as a secondary airport for Beijing, China.
  • A. BZN
    BZN is a Dutch pop band best known for its melodic, easy-listening songs and long-standing popularity in the Netherlands.
  • B. ZBYN
    ZBYN is the ICAO airport code for Taiyuan Wusu International Airport in Taiyuan, Shanxi Province, China.
  • C. BYN
    BYN is the ISO 4217 currency code for the current Belarusian ruble, the official currency of Belarus.
  • D. BBNZ
    BBNZ is the national governing body responsible for overseeing and developing the sport of basketball in New Zealand.
  • E. NYJ
    NYJ is the common abbreviation for the New York Jets, a professional American football team based in the New York metropolitan area that competes in the NFL.
  • 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_69d86dae698881908327ef2d67706cb9 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e183795100819097be92e6d07dc5b1 completed April 17, 2026, 12:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbe88a608190bc0a0cbfdb71e81d completed May 10, 2026, 1:14 a.m.
NEDg Description generation batch_69ffdce9591c81909e6bb5c13ddf84cd completed May 10, 2026, 1:18 a.m.
NED2 Entity disambiguation (via description) batch_69ffddb0ff848190ace70b55d9861040 completed May 10, 2026, 1:21 a.m.
Created at: April 10, 2026, 4:57 a.m.