Triple

T5690450
Position Surface form Disambiguated ID Type / Status
Subject Yale romanization E125415 entity
Predicate clarityComparedTo P51217 FINISHED
Object traditional ad hoc Cantonese spellings LITERAL 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: traditional ad hoc Cantonese spellings | Statement: [Yale romanization, clarityComparedTo, traditional ad hoc Cantonese spellings]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: clarityComparedTo
Context triple: [Yale romanization, clarityComparedTo, traditional ad hoc Cantonese spellings]
  • A. isEasierToSeeThan
    Indicates that one entity is more visually noticeable or discernible than another under comparable viewing conditions.
  • B. comparisonAspect chosen
    Indicates that two or more entities are being compared specifically with respect to a particular shared attribute or dimension.
  • C. clarifiesThat
    Indicates that one entity explains or makes another entity more understandable by removing ambiguity or confusion about it.
  • D. contrastCapability
    Indicates a relationship where one entity’s capabilities are compared or set in opposition to another’s, highlighting differences in what they can do or achieve.
  • E. comparisonType
    Indicates the specific kind of comparison being made between two or more values or entities (e.g., equality, inequality, ordering, or similarity).
  • F. None of above.

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_69c0082bb19c8190823a4facd3cba79b completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c029014588819094a2a0f6f9b66bab completed March 22, 2026, 5:38 p.m.
PD Predicate disambiguation batch_69c021c0e0408190ab6c3cd3f907e80f completed March 22, 2026, 5:07 p.m.
Created at: March 22, 2026, 3:44 p.m.