Triple

T16120364
Position Surface form Disambiguated ID Type / Status
Subject Li Auto E391117 entity
Predicate competesWith P1375 FINISHED
Object Xpeng Motors E323035 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: Xpeng Motors | Statement: [Li Auto, competesWith, Xpeng Motors]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Xpeng Motors
Context triple: [Li Auto, competesWith, Xpeng Motors]
  • A. XPeng chosen
    XPeng is a Chinese electric vehicle manufacturer known for its smart, tech-focused cars and advanced driver-assistance systems.
  • B. Li Auto
    Li Auto is a Chinese electric vehicle manufacturer known for its extended-range hybrid SUVs and focus on smart, family-oriented cars.
  • C. 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.
  • D. BYD
    BYD is the National Rail station code for Barry Docks railway station in the Vale of Glamorgan, Wales.
  • E. Zoomlion
    Zoomlion is a major Chinese manufacturer of construction machinery and sanitation equipment, known as one of the largest heavy equipment companies in China.
  • 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_69d87f1a8dd881909f1de6ef78849874 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e20200acac8190a47e6a917ff8dd34 completed April 17, 2026, 9:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff79ecea0819083aa5cb676d49f64 completed May 10, 2026, 3:12 a.m.
Created at: April 10, 2026, 5 a.m.