Triple

T6177560
Position Surface form Disambiguated ID Type / Status
Subject Xi'an Xianyang International Airport E137857 entity
Predicate ICAOcode P419 FINISHED
Object ZLXY
ZLXY is the ICAO airport code assigned to Xi'an Xianyang International Airport in Shaanxi, China.
 E574474 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: ZLXY | Statement: [Xi'an Xianyang International Airport, ICAOcode, ZLXY]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ZLXY
Context triple: [Xi'an Xianyang International Airport, ICAOcode, ZLXY]
  • A. ZLP
    ZLP is the IATA station code for Zürich Hauptbahnhof, the main railway station in Zurich, Switzerland.
  • B. LZB
    LZB is a continuous automatic train control and cab signaling system used on high-speed and heavy-traffic railway lines, particularly in Germany and neighboring countries.
  • C. ZYTX
    ZYTX is the ICAO airport code for Shenyang Taoxian International Airport, a major airport serving Shenyang in northeastern China.
  • D. WZL-1
    WZL-1 is a major Polish aerospace and defense company specializing in the maintenance, repair, and modernization of military aircraft and related systems.
  • E. ZWL
    ZWL is the currency code for the reintroduced Zimbabwean dollar used in Zimbabwe’s monetary system.
  • 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: ZLXY
Triple: [Xi'an Xianyang International Airport, ICAOcode, ZLXY]
Generated description
ZLXY is the ICAO airport code assigned to Xi'an Xianyang International Airport in Shaanxi, China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ZLXY
Target entity description: ZLXY is the ICAO airport code assigned to Xi'an Xianyang International Airport in Shaanxi, China.
  • A. ZLP
    ZLP is the IATA station code for Zürich Hauptbahnhof, the main railway station in Zurich, Switzerland.
  • B. LZB
    LZB is a continuous automatic train control and cab signaling system used on high-speed and heavy-traffic railway lines, particularly in Germany and neighboring countries.
  • C. ZYTX
    ZYTX is the ICAO airport code for Shenyang Taoxian International Airport, a major airport serving Shenyang in northeastern China.
  • D. WZL-1
    WZL-1 is a major Polish aerospace and defense company specializing in the maintenance, repair, and modernization of military aircraft and related systems.
  • E. ZWL
    ZWL is the currency code for the reintroduced Zimbabwean dollar used in Zimbabwe’s monetary system.
  • 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_69c008a80f748190ba3d07ffc81acb29 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c05dc87bc48190834042d9c41d5b86 completed March 22, 2026, 9:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c141bb426881908d5a1451b3619f03 completed March 23, 2026, 1:35 p.m.
NEDg Description generation batch_69c1467ef4d48190b714823935318c0a completed March 23, 2026, 1:56 p.m.
NED2 Entity disambiguation (via description) batch_69c146f59d9881908fdc6c0137f0ead7 completed March 23, 2026, 1:58 p.m.
Created at: March 22, 2026, 4:18 p.m.