Triple

T13182723
Position Surface form Disambiguated ID Type / Status
Subject Rijeka Airport E313768 entity
Predicate ICAOcode P419 FINISHED
Object LDRI
LDRI is the ICAO airport code for Rijeka Airport, a commercial airport serving the city of Rijeka and the Kvarner region in Croatia.
 E1026926 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: LDRI | Statement: [Rijeka Airport, ICAOcode, LDRI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LDRI
Context triple: [Rijeka Airport, ICAOcode, LDRI]
  • A. LDI
    LDI is the stock ticker symbol for loanDepot, a U.S.-based nonbank mortgage lender and financial services company.
  • B. LDR
    LDR is a centrist-liberal political group known as the Liberal and Democratic Reformist Group.
  • C. LRD
    LRD is the official currency code for the Liberian dollar, the legal tender used in Liberia.
  • D. DR1
    DR1 is Denmark’s primary national television channel, operated by the public broadcaster DR and known for producing high-quality Danish drama and news programming.
  • E. LD
    LD is the IATA airline designator assigned to Air Hong Kong, a cargo airline based in Hong Kong.
  • 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: LDRI
Triple: [Rijeka Airport, ICAOcode, LDRI]
Generated description
LDRI is the ICAO airport code for Rijeka Airport, a commercial airport serving the city of Rijeka and the Kvarner region in Croatia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LDRI
Target entity description: LDRI is the ICAO airport code for Rijeka Airport, a commercial airport serving the city of Rijeka and the Kvarner region in Croatia.
  • A. LDI
    LDI is the stock ticker symbol for loanDepot, a U.S.-based nonbank mortgage lender and financial services company.
  • B. LDR
    LDR is a centrist-liberal political group known as the Liberal and Democratic Reformist Group.
  • C. LRD
    LRD is the official currency code for the Liberian dollar, the legal tender used in Liberia.
  • D. DR1
    DR1 is Denmark’s primary national television channel, operated by the public broadcaster DR and known for producing high-quality Danish drama and news programming.
  • E. LD
    LD is the IATA airline designator assigned to Air Hong Kong, a cargo airline based in Hong Kong.
  • 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_69d806ae1e08819090d95bfe1538cc17 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c4a0b0081908027bf77442ff5ff completed April 10, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5f307408190afd0df16a417c456 completed May 3, 2026, 7:14 a.m.
NEDg Description generation batch_69f6f707d9e48190b772520ca9f4ac2c completed May 3, 2026, 7:19 a.m.
NED2 Entity disambiguation (via description) batch_69f6f85149cc8190adf68387475d3286 completed May 3, 2026, 7:25 a.m.
Created at: April 9, 2026, 9:15 p.m.