Triple

T5103154
Position Surface form Disambiguated ID Type / Status
Subject OFDM E115027 entity
Predicate appliedIn P1129 FINISHED
Object ADSL E216139 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: ADSL | Statement: [OFDM, appliedIn, ADSL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ADSL
Context triple: [OFDM, appliedIn, ADSL]
  • A. xDSL technologies chosen
    xDSL technologies are a family of digital subscriber line standards that provide high-speed data transmission over traditional copper telephone lines for broadband internet access.
  • B. BT broadband
    BT broadband is a UK-based internet service provided by BT Group, offering fixed-line broadband connections and related digital services to residential and business customers.
  • C. V.90
    V.90 is an ITU-T modem standard that enabled dial-up internet connections at speeds up to 56 kbit/s over traditional telephone lines.
  • D. DOCSIS
    DOCSIS is an international telecommunications standard that enables high-speed data transmission over existing cable television systems, commonly used for broadband internet services.
  • E. V.92
    V.92 is an ITU-T modem standard that defines enhanced dial-up Internet connection features such as faster upload speeds, quicker call setup, and modem-on-hold capabilities.
  • 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_69bd4440b3348190be1251fd8b7951f1 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd7586a4a08190866aea6be625837c completed March 20, 2026, 4:27 p.m.
NED1 Entity disambiguation (via context triple) batch_69beba9106ec8190839a7de183efa359 completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:41 p.m.