Triple

T4392948
Position Surface form Disambiguated ID Type / Status
Subject Bern Airport E99408 entity
Predicate hasICAOcode P419 FINISHED
Object LSZB
LSZB is the ICAO airport code for Bern Airport, the primary airport serving Switzerland’s capital city.
 E436105 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: LSZB | Statement: [Bern Airport, hasICAOcode, LSZB]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: LSZB
Context triple: [Bern Airport, hasICAOcode, LSZB]
  • A. 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.
  • B. LZ
    LZ is the stock ticker symbol for The Lubrizol Corporation, a specialty chemicals company known for its lubricant additives and advanced materials.
  • C. ZS
    ZS is the vehicle registration code assigned to cars registered in the Polish city of Szczecin.
  • D. BANZSL
    BANZSL is the family of closely related sign languages used in Britain, Australia, and New Zealand, sharing a common historical origin and many linguistic features.
  • E. ZBH
    ZBH is the stock ticker symbol for Zimmer Biomet Holdings, Inc., a major medical device company specializing in musculoskeletal healthcare products.
  • 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: LSZB
Triple: [Bern Airport, hasICAOcode, LSZB]
Generated description
LSZB is the ICAO airport code for Bern Airport, the primary airport serving Switzerland’s capital city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: LSZB
Target entity description: LSZB is the ICAO airport code for Bern Airport, the primary airport serving Switzerland’s capital city.
  • A. 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.
  • B. LZ
    LZ is the stock ticker symbol for The Lubrizol Corporation, a specialty chemicals company known for its lubricant additives and advanced materials.
  • C. ZS
    ZS is the vehicle registration code assigned to cars registered in the Polish city of Szczecin.
  • D. BANZSL
    BANZSL is the family of closely related sign languages used in Britain, Australia, and New Zealand, sharing a common historical origin and many linguistic features.
  • E. ZBH
    ZBH is the stock ticker symbol for Zimmer Biomet Holdings, Inc., a major medical device company specializing in musculoskeletal healthcare products.
  • 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_69b345506b408190b0e3dee616738a7d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352a8862481909dc67abf42be6928 completed March 12, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e53385508190ac1261c44672070b completed March 14, 2026, 10:46 p.m.
NEDg Description generation batch_69b5e666bcbc819083bbb60309d689e7 completed March 14, 2026, 10:51 p.m.
NED2 Entity disambiguation (via description) batch_69b5e6c780248190a2101f35f47ae374 completed March 14, 2026, 10:52 p.m.
Created at: March 12, 2026, 11:19 p.m.