Triple

T15227591
Position Surface form Disambiguated ID Type / Status
Subject G.E. Thomas E363914 entity
Predicate knownFor P22 FINISHED
Object Manchester encoding E74022 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: Manchester encoding | Statement: [G.E. Thomas, knownFor, Manchester encoding]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Manchester encoding
Context triple: [G.E. Thomas, knownFor, Manchester encoding]
  • A. Manchester encoding chosen
    Manchester encoding is a digital line code that represents each data bit with a transition in the middle of the bit period, providing both clock and data synchronization on the same signal.
  • B. Scott encoding
    Scott encoding is a method in lambda calculus for representing algebraic data types and their pattern matching behavior using higher-order functions.
  • C. NRZI
    NRZI (Non-Return-to-Zero Inverted) is a digital line coding scheme that represents binary data by inverting the signal level on a '1' and leaving it unchanged on a '0', commonly used in various networking and storage technologies.
  • D. NRZ-L
    NRZ-L (Non-Return-to-Zero-Level) is a digital line coding scheme in which binary data is represented by two distinct voltage levels that remain constant throughout each bit interval.
  • E. Hamming code
    Hamming code is a family of error-detecting and error-correcting binary codes that enable the automatic detection and correction of single-bit errors in transmitted or stored data.
  • 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_69d85a0ce24c81909c4d3b6475548c95 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0078ccdf48190b34eabd9e24e45a1 completed April 15, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69fedd379ac081909ebb3a18c2ee3b3c completed May 9, 2026, 7:07 a.m.
Created at: April 10, 2026, 3:12 a.m.