Triple

T22585012
Position Surface form Disambiguated ID Type / Status
Subject Unicode normalization E564765 entity
Predicate hasFullName P16 FINISHED
Object Normalization Form KD
Normalization Form KD is a Unicode text normalization form that converts characters to their compatibility decomposed equivalents to ensure consistent text representation.
 E1546464 NE FINISHED

How this triple was built (4 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: Normalization Form KD | Statement: [Unicode normalization, hasFullName, Normalization Form KD]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Normalization Form KD
Context triple: [Unicode normalization, hasFullName, Normalization Form KD]
  • A. NFD
    NFD is the National Rail station code for Northfield railway station in Birmingham, England.
  • B. KNF
    KNF is the IATA airport code for RAF Marham, a Royal Air Force station in Norfolk, England.
  • C. KNF
    KNF is the National Rail station code for Knutsford railway station in Cheshire, England.
  • D. DKD
    DKD is the National Rail station code for Dunkeld and Birnam railway station in Scotland.
  • E. NKC
    NKC is the National Kriol Council of Belize, an organization dedicated to preserving and promoting Belizean Kriol language and culture.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Normalization Form KD
Triple: [Unicode normalization, hasFullName, Normalization Form KD]
Generated description
Normalization Form KD is a Unicode text normalization form that converts characters to their compatibility decomposed equivalents to ensure consistent text representation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Normalization Form KD
Target entity description: Normalization Form KD is a Unicode text normalization form that converts characters to their compatibility decomposed equivalents to ensure consistent text representation.
  • A. NFD
    NFD is the National Rail station code for Northfield railway station in Birmingham, England.
  • B. KNF
    KNF is the IATA airport code for RAF Marham, a Royal Air Force station in Norfolk, England.
  • C. KNF
    KNF is the National Rail station code for Knutsford railway station in Cheshire, England.
  • D. DKD
    DKD is the National Rail station code for Dunkeld and Birnam railway station in Scotland.
  • E. NKC
    NKC is the National Kriol Council of Belize, an organization dedicated to preserving and promoting Belizean Kriol language and culture.
  • F. None of above. chosen

Provenance (5 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_69e245836014819091b91ed3074742a3 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1615c18f88190ad4f23639d15f337 completed April 29, 2026, 1:39 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b4df155e881909d68b23e61d2bfb2 completed May 18, 2026, 5:35 p.m.
NEDg Description generation batch_6a0b51f28ffc81909792131738d8ea93 completed May 18, 2026, 5:52 p.m.
NED2 Entity disambiguation (via description) batch_6a0b525e0cf08190a8b18165034d3d30 completed May 18, 2026, 5:54 p.m.
Created at: April 17, 2026, 2:45 p.m.