Triple

T8202399
Position Surface form Disambiguated ID Type / Status
Subject Shiyan Wudangshan Airport E191609 entity
Predicate hasICAOCode P419 FINISHED
Object ZHSY
ZHSY is the ICAO airport code assigned to Shiyan Wudangshan Airport in Hubei Province, China.
 E718708 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: ZHSY | Statement: [Shiyan Wudangshan Airport, hasICAOCode, ZHSY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ZHSY
Context triple: [Shiyan Wudangshan Airport, hasICAOCode, ZHSY]
  • A. HSZG
    HSZG is a German University of Applied Sciences located in the twin cities of Zittau and Görlitz, offering practice-oriented higher education and research programs.
  • B. ZGSZ
    ZGSZ is the ICAO airport code for Shenzhen Bao’an International Airport, a major aviation hub serving the city of Shenzhen in Guangdong, China.
  • C. YHZ
    YHZ is the IATA airport code for Halifax Stanfield International Airport, the primary commercial airport serving Halifax and much of Atlantic Canada.
  • D. ZCHS
    ZCHS is a public high school serving the Zionsville, Indiana community, known for its strong academics and extracurricular programs.
  • E. ZHES
    ZHES is the ICAO airport code assigned to Enshi Xujiaping Airport in Hubei Province, China.
  • 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: ZHSY
Triple: [Shiyan Wudangshan Airport, hasICAOCode, ZHSY]
Generated description
ZHSY is the ICAO airport code assigned to Shiyan Wudangshan Airport in Hubei Province, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ZHSY
Target entity description: ZHSY is the ICAO airport code assigned to Shiyan Wudangshan Airport in Hubei Province, China.
  • A. HSZG
    HSZG is a German University of Applied Sciences located in the twin cities of Zittau and Görlitz, offering practice-oriented higher education and research programs.
  • B. ZGSZ
    ZGSZ is the ICAO airport code for Shenzhen Bao’an International Airport, a major aviation hub serving the city of Shenzhen in Guangdong, China.
  • C. YHZ
    YHZ is the IATA airport code for Halifax Stanfield International Airport, the primary commercial airport serving Halifax and much of Atlantic Canada.
  • D. ZCHS
    ZCHS is a public high school serving the Zionsville, Indiana community, known for its strong academics and extracurricular programs.
  • E. ZHES
    ZHES is the ICAO airport code assigned to Enshi Xujiaping Airport in Hubei Province, China.
  • 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_69ca82c7f3e08190857bf1fc63b2a10c completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb5df84b108190b4407a72a3500af9 completed March 31, 2026, 5:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccedc49ba4819099762f200c4e6577 completed April 1, 2026, 10:04 a.m.
NEDg Description generation batch_69ccf1b818588190936f96d53bf08c2b completed April 1, 2026, 10:21 a.m.
NED2 Entity disambiguation (via description) batch_69cd05ac594c819087d23a7318fd7704 completed April 1, 2026, 11:46 a.m.
Created at: March 30, 2026, 5:43 p.m.