Triple

T2088439
Position Surface form Disambiguated ID Type / Status
Subject SAN E32609 entity
Predicate airportLocationState P26493 FINISHED
Object California E26 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: California | Statement: [SAN, airportLocationState, California]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: California
Context triple: [SAN, airportLocationState, California]
  • A. California, United States chosen
    California, United States is a large and populous U.S. state on the West Coast known for its diverse geography, major technology and entertainment industries, and cultural and economic influence.
  • B. CA
    CA is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Canada in international standards and systems.
  • C. CA
    CA is the IATA airline designator assigned to Air China, the flag carrier of the People's Republic of China.
  • D. CA
    CA is the two-letter U.S. postal abbreviation for the state of California.
  • E. California, Pennsylvania
    California, Pennsylvania is a small borough in southwestern Pennsylvania best known as the home of PennWest California (formerly California University of Pennsylvania) along the Monongahela River.
  • 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: airportLocationState
Context triple: [SAN, airportLocationState, California]
  • A. stateOrTerritory
    Indicates that one entity is a state or territory that is politically or administratively associated with another entity.
  • B. stateName
    Indicates that an entity is identified by or associated with a particular state’s name.
  • C. hostProvinceOrState chosen
    Indicates that one administrative province or state serves as the host or location for another entity, such as an event, organization, or facility.
  • D. stateNickname
    Indicates that one entity is the commonly used nickname or informal moniker for a given state.
  • E. hasRegionalAirport
    Indicates that a place or region possesses or is served by a regional airport.
  • 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_69a885eba0708190999696a45cbec816 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abba712388819091d68a4bb99f6b17 completed March 7, 2026, 5:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea84f698081909e89bbeefd7d0894 completed March 9, 2026, 11 a.m.
PD Predicate disambiguation batch_69abb7b4356881909217c42ccb8bb1ed completed March 7, 2026, 5:29 a.m.
Created at: March 4, 2026, 7:43 p.m.