Triple

T4171965
Position Surface form Disambiguated ID Type / Status
Subject TikTok E84583 entity
Predicate hasRegionalHeadquarters P40187 FINISHED
Object Los Angeles E715 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: Los Angeles | Statement: [TikTok, hasRegionalHeadquarters, Los Angeles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Los Angeles
Context triple: [TikTok, hasRegionalHeadquarters, Los Angeles]
  • A. Los Angeles chosen
    Los Angeles is a major U.S. metropolis known for its entertainment industry, cultural diversity, and sprawling urban landscape.
  • B. Los Ángeles
    Los Ángeles is a mid-sized Chilean city known as an important commercial and agricultural center in the south-central part of the country.
  • C. San Angeles
    San Angeles is a fictional futuristic megacity formed from the merger of Los Angeles and San Diego in the science fiction film "Demolition Man."
  • D. San Fransokyo
    San Fransokyo is a fictional futuristic hybrid city combining elements of San Francisco and Tokyo, serving as the primary setting of Disney's animated film "Big Hero 6."
  • E. Santa Monica
    Santa Monica is a coastal city in western Los Angeles County, California, known for its iconic pier, beaches, and vibrant tourism and entertainment scene.
  • 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: hasRegionalHeadquarters
Context triple: [TikTok, hasRegionalHeadquarters, Los Angeles]
  • A. hasHeadquartersType
    Indicates the specific kind or classification of headquarters associated with an entity.
  • B. hasHeadquartersInRegion chosen
    Indicates that an organization’s main administrative or corporate headquarters is located within a specified geographic region.
  • C. continentHeadquarters
    Indicates that an entity’s main headquarters is located on a specified continent.
  • D. regionalOrganizationHeadquarters
    Indicates that a regional organization’s main administrative or governing offices are located at a specific place.
  • E. hasHeadquartersBuilding
    Indicates that an organization possesses a specific building that serves as its headquarters location.
  • 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_69aed932cab48190b80ffe35f7029ae1 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af02c9e12c81908d0b22671fea2453 completed March 9, 2026, 5:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f10d1008190a3bbe93c1215a244 completed March 14, 2026, 3:30 p.m.
PD Predicate disambiguation batch_69af018fb0948190a9701b2e8e5d9bac completed March 9, 2026, 5:21 p.m.
Created at: March 9, 2026, 3:45 p.m.