Triple

T17537398
Position Surface form Disambiguated ID Type / Status
Subject Tensor G3 E427096 entity
Predicate manufacturer P490 FINISHED
Object Samsung NE NERFINISHED

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: Samsung | Statement: [Tensor G3, manufacturer, Samsung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samsung
Context triple: [Tensor G3, manufacturer, Samsung]
  • A. Samsung chosen
    Samsung is a South Korean multinational conglomerate best known globally for its smartphones, consumer electronics, and advanced semiconductor technologies.
  • B. Samsung Group
    Samsung Group is a South Korean multinational conglomerate best known globally for its consumer electronics, particularly smartphones, tablets, and televisions, as well as its significant presence in semiconductors and other industries.
  • C. Samsung Pass
    Samsung Pass was Samsung’s biometric authentication and password management service that let users securely log into apps and websites using features like fingerprint or iris recognition.
  • D. Samsung C&T
    Samsung C&T is a South Korean construction and trading company known for executing major global projects, including landmark skyscrapers and large-scale infrastructure.
  • E. LG Electronics
    LG Electronics is a South Korean multinational electronics company known for producing a wide range of consumer electronics, home appliances, and mobile devices.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4536d03dc81908b8a58f66657c01a completed April 19, 2026, 4 a.m.
Created at: April 10, 2026, 5:49 a.m.