Triple

T1711554
Position Surface form Disambiguated ID Type / Status
Subject Düsseldorf E36993 entity
Predicate airportIATA P418 FINISHED
Object DUS
DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
 E193731 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: DUS | Statement: [Düsseldorf, airportIATA, DUS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DUS
Context triple: [Düsseldorf, airportIATA, DUS]
  • A. DU
    DU is a premier public central university in India, renowned for its diverse academic programs and large collegiate system based in New Delhi.
  • B. DSU
    DSU is the World Trade Organization’s legal framework that sets out the rules and procedures for resolving trade disputes between member countries.
  • C. DSS
    DSS is the abbreviated name of the Securitate, the notorious secret police service of Communist Romania.
  • D. DUCET
    DUCET is the Default Unicode Collation Element Table, a standard reference used to define the sorting and comparison order of Unicode characters across different languages and scripts.
  • E. Tus
    Tus is an ancient city in northeastern Iran, renowned as a cultural and literary center and traditionally regarded as the birthplace and home of the Persian epic poet Ferdowsi.
  • 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: DUS
Triple: [Düsseldorf, airportIATA, DUS]
Generated description
DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DUS
Target entity description: DUS is the three-letter IATA code for Düsseldorf Airport, a major international airport in western Germany.
  • A. DU
    DU is a premier public central university in India, renowned for its diverse academic programs and large collegiate system based in New Delhi.
  • B. DSU
    DSU is the World Trade Organization’s legal framework that sets out the rules and procedures for resolving trade disputes between member countries.
  • C. DSS
    DSS is the abbreviated name of the Securitate, the notorious secret police service of Communist Romania.
  • D. DUCET
    DUCET is the Default Unicode Collation Element Table, a standard reference used to define the sorting and comparison order of Unicode characters across different languages and scripts.
  • E. Tus
    Tus is an ancient city in northeastern Iran, renowned as a cultural and literary center and traditionally regarded as the birthplace and home of the Persian epic poet Ferdowsi.
  • 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_69a88617439c819094ffb5d16a0f6307 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa63149288819082e7055d0d292d1d completed March 6, 2026, 5:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad8addf4a48190b19cdb861db5eecd completed March 8, 2026, 2:42 p.m.
NEDg Description generation batch_69ad957912808190be5b6ed8d3f20535 completed March 8, 2026, 3:27 p.m.
NED2 Entity disambiguation (via description) batch_69ad97accca48190bc43e94337589a5f completed March 8, 2026, 3:37 p.m.
Created at: March 4, 2026, 7:30 p.m.