Triple

T3925111
Position Surface form Disambiguated ID Type / Status
Subject Roewe E93255 entity
Predicate competesWith P1375 FINISHED
Object Geely E320412 NE FINISHED

How this triple was built (2 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: Geely | Statement: [Roewe, competesWith, Geely]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geely
Context triple: [Roewe, competesWith, Geely]
  • A. Zhejiang Geely Holding Group chosen
    Zhejiang Geely Holding Group is a major Chinese multinational automotive conglomerate known for owning global car brands such as Volvo Cars and Geely Auto.
  • B. BYD Auto
    BYD Auto is a major Chinese automobile manufacturer best known for its electric and hybrid vehicles and rapid global expansion in the new energy vehicle market.
  • C. Chery Automobile
    Chery Automobile is a major Chinese state-owned car manufacturer known for producing affordable passenger vehicles and exporting them to numerous international markets.
  • D. Jiangling
    Jiangling was an important ancient Chinese city that served as a major political and cultural center of the State of Chu during the Zhou dynasty period.
  • E. SAIC Motor
    SAIC Motor is a major Chinese state-owned automotive manufacturer and one of the country’s largest carmakers, producing vehicles under its own brands and through joint ventures with global and regional partners.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed96bfa1081908f7b30f2c647dee6 completed March 9, 2026, 2:30 p.m.
NER Named-entity recognition batch_69aeed7f3cc881909464db1970ba39ae completed March 9, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b52873d5a881909c4c29f06b94a467 completed March 14, 2026, 9:20 a.m.
Created at: March 9, 2026, 3:23 p.m.