Triple

T5066255
Position Surface form Disambiguated ID Type / Status
Subject Port of Tallinn E114150 entity
Predicate hasIcaoCode P419 FINISHED
Object EEPU
EEPU is the ICAO airport code for the Port of Tallinn’s associated airfield in Estonia.
 E489993 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: EEPU | Statement: [Port of Tallinn, hasIcaoCode, EEPU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: EEPU
Context triple: [Port of Tallinn, hasIcaoCode, EEPU]
  • A. EPKK
    EPKK is the ICAO airport code for John Paul II International Airport Kraków–Balice, the main international airport serving Kraków in southern Poland.
  • B. EPP
    EPP is a major center-right, pro-European political party at the European level, bringing together Christian democratic and conservative parties from across the European Union.
  • C. EBB
    EBB is the common abbreviation for Eisbären Berlin, a professional ice hockey team based in Berlin, Germany.
  • D. EP&S
    EP&S is the abbreviated name for Sony’s Electronics Products & Solutions business segment, which encompasses its core consumer and professional electronics operations.
  • E. EP
    The EP is the directly elected legislative body of the European Union that works with other EU institutions to pass laws and oversee policies across member states.
  • 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: EEPU
Triple: [Port of Tallinn, hasIcaoCode, EEPU]
Generated description
EEPU is the ICAO airport code for the Port of Tallinn’s associated airfield in Estonia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: EEPU
Target entity description: EEPU is the ICAO airport code for the Port of Tallinn’s associated airfield in Estonia.
  • A. EPKK
    EPKK is the ICAO airport code for John Paul II International Airport Kraków–Balice, the main international airport serving Kraków in southern Poland.
  • B. EPP
    EPP is a major center-right, pro-European political party at the European level, bringing together Christian democratic and conservative parties from across the European Union.
  • C. EBB
    EBB is the common abbreviation for Eisbären Berlin, a professional ice hockey team based in Berlin, Germany.
  • D. EP&S
    EP&S is the abbreviated name for Sony’s Electronics Products & Solutions business segment, which encompasses its core consumer and professional electronics operations.
  • E. EP
    The EP is the directly elected legislative body of the European Union that works with other EU institutions to pass laws and oversee policies across member states.
  • 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_69bd443c0c8c81908663b77afb28e165 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd749aceac8190817278266308fd64 completed March 20, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea49d917081909ead17eed3f8af90 completed March 21, 2026, 2:01 p.m.
NEDg Description generation batch_69bea525d9088190b0b655687dd27630 completed March 21, 2026, 2:03 p.m.
NED2 Entity disambiguation (via description) batch_69bea594850881909cd683670b63a079 completed March 21, 2026, 2:05 p.m.
Created at: March 20, 2026, 1:38 p.m.