Triple

T3384242
Position Surface form Disambiguated ID Type / Status
Subject ASML E71257 entity
Predicate keyCustomer P927 FINISHED
Object TSMC E38958 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: TSMC | Statement: [ASML, keyCustomer, TSMC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TSMC
Context triple: [ASML, keyCustomer, TSMC]
  • A. TSMC chosen
    TSMC (Taiwan Semiconductor Manufacturing Company) is the world’s largest dedicated semiconductor foundry, renowned for producing cutting-edge chips for major technology companies.
  • B. Micron Technology
    Micron Technology is a leading American semiconductor company known for designing and manufacturing memory and storage solutions, including DRAM and NAND flash products used in computers, mobile devices, and data centers.
  • C. GlobalFoundries
    GlobalFoundries is a major multinational semiconductor foundry that manufactures integrated circuits for a wide range of global technology companies.
  • D. Infineon Technologies
    Infineon Technologies is a leading German semiconductor manufacturer known for its automotive, power, and security electronics solutions.
  • E. SK hynix
    SK hynix is a South Korean semiconductor company and one of the world’s leading manufacturers of memory chips, including DRAM and NAND flash.
  • 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_69ad85a8fd9c819095ecedf838d2bf1b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb5ec85d08190b28110157c39435f completed March 8, 2026, 5:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b33452d79081909bf6955289e0dece completed March 12, 2026, 9:46 p.m.
Created at: March 8, 2026, 3:14 p.m.