Triple

T568725
Position Surface form Disambiguated ID Type / Status
Subject TXL E13614 entity
Predicate associatedWithCityCode P6089 FINISHED
Object BER E71200 NE FINISHED

How this triple was built (3 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: BER | Statement: [TXL, associatedWithCityCode, BER]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BER
Context triple: [TXL, associatedWithCityCode, BER]
  • A. BER chosen
    BER is Berlin Brandenburg Airport, the main international airport serving Germany’s capital region.
  • B. BEL
    BEL is the three-letter ISO 3166-1 alpha-3 country code that uniquely identifies Belgium in international standards and data systems.
  • C. BE
    BE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Belgium in international standards and systems.
  • D. Be
    "Be" is the critically acclaimed 2005 hip-hop album by Chicago rapper Common, celebrated for its soulful production by Kanye West and J Dilla and its introspective, socially conscious lyrics.
  • E. BO
    BO is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Bolivia in international standards and systems.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: associatedWithCityCode
Context triple: [TXL, associatedWithCityCode, BER]
  • A. linkedCity
    Indicates that two entities are associated with each other through a specific city, such as being located in, connected via, or related by that city.
  • B. associatedWithCounty
    Indicates that an entity has a relationship or linkage to a specific county, such as jurisdiction, location, or administrative association.
  • C. hasAirportCodeCity chosen
    Indicates that a city is associated with a specific airport code (such as an IATA or ICAO code) that identifies its airport.
  • D. associatedWithIATAAirlineCode
    Indicates that an entity is linked to or identified by a specific IATA airline code.
  • E. connectsCity
    Indicates a relationship where one entity serves as a link or route that joins or provides direct access between two cities.
  • F. None of above.

Provenance (4 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_69a4933fa4d88190a7949cc83c08c5c1 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a49b0406d481908af5fc7bc67103fb completed March 1, 2026, 8:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4fc81d6d4819090d91560efaa085d completed March 2, 2026, 2:57 a.m.
PD Predicate disambiguation batch_69a494c2caac819086ab316fa49d324c completed March 1, 2026, 7:34 p.m.
Created at: March 1, 2026, 7:33 p.m.