Triple

T14008639
Position Surface form Disambiguated ID Type / Status
Subject Sinovac E337018 entity
Predicate regulatoryApprovalForCoronaVac P24602 FINISHED
Object China E5561 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: China | Statement: [Sinovac, regulatoryApprovalForCoronaVac, China]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: China
Context triple: [Sinovac, regulatoryApprovalForCoronaVac, China]
  • A. China chosen
    China is a vast East Asian country known for its long continuous civilization, large population, and major global economic and political influence.
  • B. Kinas
    Kinas is the official rooster mascot created for the UEFA Euro 2004 football championship held in Portugal.
  • C. Çine
    Çine is a district and town in southwestern Turkey known for its agricultural activities and location within Aydın Province in the Aegean region.
  • D. Chung Kuo
    "Chung Kuo" is an instrumental electronic music track by Vangelis from his 1979 album "China," evoking an atmospheric, synthesizer-driven portrait of China.
  • E. kina
    Kina is the official currency of Papua New Guinea, used for everyday transactions and financial activities throughout the country.
  • 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: regulatoryApprovalForCoronaVac
Context triple: [Sinovac, regulatoryApprovalForCoronaVac, China]
  • A. hasRegulatoryApproval chosen
    Indicates that an entity has received formal authorization or clearance from a relevant regulatory authority to operate, be sold, or be used in a specified context.
  • B. covid19VaccineType
    Indicates the specific type or category of COVID-19 vaccine associated with an entity.
  • C. FDAApprovalType
    Indicates the specific regulatory pathway or category under which a product has been approved by the U.S. Food and Drug Administration.
  • D. regulatoryApprovalYear
    Indicates the calendar year in which an official regulatory body granted approval for the referenced item, action, or entity.
  • E. vaccineUsed
    Indicates that a particular vaccine has been administered or applied in a given medical or experimental context.
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2ed44f90819099ad08c09c066b56 completed April 14, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdef5e0648190ace4ec1605968e30 completed May 7, 2026, 6:50 p.m.
PD Predicate disambiguation batch_69dd465dfbc4819090d8c61fd572d35f completed April 13, 2026, 7:39 p.m.
Created at: April 9, 2026, 10:19 p.m.