Triple

T7279094
Position Surface form Disambiguated ID Type / Status
Subject Intel SGX E163103 entity
Predicate abbreviation P43 FINISHED
Object SGX E163103 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: SGX | Statement: [Intel SGX, abbreviation, SGX]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SGX
Context triple: [Intel SGX, abbreviation, SGX]
  • A. Intel SGX chosen
    Intel SGX is a hardware-based security technology that enables the creation of protected enclaves in memory to run sensitive code and data in isolation from the rest of the system.
  • B. SGC
    SGC is the station code for St George's Cross, a Glasgow Subway station in Scotland.
  • C. SECG
    SECG (Standards for Efficient Cryptography Group) is an industry consortium that develops and promotes standards for efficient public-key cryptography, particularly elliptic curve cryptography.
  • D. SIGA Technologies
    SIGA Technologies is a pharmaceutical company specializing in the development of antiviral treatments, particularly for smallpox and other orthopoxvirus infections.
  • E. G2X
    G2X is a compact sports car model produced by Daewoo (also known as the Daewoo G2X), recognized for its sleek design and performance-oriented features.
  • 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_69c6885c5964819085b209701769877f completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6eb3251808190bd9da71bc183c945 completed March 27, 2026, 8:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7db3450208190b67e4329a531ad0c completed March 28, 2026, 1:44 p.m.
Created at: March 27, 2026, 2:59 p.m.