Triple

T14478300
Position Surface form Disambiguated ID Type / Status
Subject Vunisea Airport E359032 entity
Predicate ICAOcode P419 FINISHED
Object NFKD E564765 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: NFKD | Statement: [Vunisea Airport, ICAOcode, NFKD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NFKD
Context triple: [Vunisea Airport, ICAOcode, NFKD]
  • A. Unicode normalization chosen
    Unicode normalization is a set of standardized processes that convert equivalent Unicode text sequences into a consistent canonical form to ensure reliable comparison, searching, and processing of text across systems.
  • B. UNGEGN Arabic romanization system
    The UNGEGN Arabic romanization system is a United Nations-approved standard for systematically converting Arabic script into Latin characters for consistent international use in geographic names and related contexts.
  • C. Unicode Technical Standard #10
    Unicode Technical Standard #10 is the specification that defines the Unicode Collation Algorithm, providing a standardized method for comparing and sorting Unicode text across languages and platforms.
  • D. Unicode Technical Standard #35
    Unicode Technical Standard #35 is a Unicode Consortium specification that defines the Locale Data Markup Language (LDML) and related mechanisms for internationalization, including formatting of dates, times, numbers, and other locale-sensitive data.
  • E. CJK Compatibility Ideographs
    CJK Compatibility Ideographs is a Unicode block that contains duplicate or variant Chinese, Japanese, and Korean characters included mainly for backward compatibility with older character encoding standards.
  • 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_69d827966698819082e140837737501d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de9248edb48190a74eb032aeaac027 completed April 14, 2026, 7:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd64a257488190818c65c1cc84c4b5 completed May 8, 2026, 4:20 a.m.
Created at: April 10, 2026, 1:20 a.m.