Triple

T26790664
Position Surface form Disambiguated ID Type / Status
Subject Kitan Strait E670508 entity
Predicate hasNameRomanized P164578 FINISHED
Object Kitan Kaikyō
Kitan Kaikyō is the Japanese name for the Kitan Strait, a narrow sea passage off the coast of Japan.
 E1741383 NE FINISHED

How this triple was built (3 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: Kitan Kaikyō | Statement: [Kitan Strait, hasNameRomanized, Kitan Kaikyō]
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: Kitan Kaikyō
Triple: [Kitan Strait, hasNameRomanized, Kitan Kaikyō]
Generated description
Kitan Kaikyō is the Japanese name for the Kitan Strait, a narrow sea passage off the coast of Japan.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasNameRomanized
Context triple: [Kitan Strait, hasNameRomanized, Kitan Kaikyō]
  • A. nameInLanguageRomanization chosen
    Indicates that an entity’s name is represented in the romanized (Latin-script) form of a particular language.
  • B. hasRomanizationOf
    Indicates that one entity is a romanized representation (written in the Latin alphabet) of the other entity’s original script form.
  • C. hangulNameRomanized
    Indicates that an entity’s Korean Hangul name is represented in its romanized (Latin alphabet) form.
  • D. hasRomanizationStandard
    Indicates that an entity’s romanized form follows a specified romanization standard or system.
  • E. hasNameInKanji
    Indicates that an entity is associated with a specific written form of its name in Kanji characters.
  • F. None of above.

Provenance (6 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_69eeb31d45f8819089f52ebdbc556218 completed April 27, 2026, 12:51 a.m.
NER Named-entity recognition batch_69f7308a096081909d66a56f3c926806 completed May 3, 2026, 11:24 a.m.
NED1 Entity disambiguation (via context triple) batch_6a120964970c8190826373f6dbd1afdc completed May 23, 2026, 8:09 p.m.
NEDg Description generation batch_6a120aa69a8c819083a6dc95e4d6382e completed May 23, 2026, 8:14 p.m.
NED2 Entity disambiguation (via description) batch_6a120b329b30819089e007135e13dc21 completed May 23, 2026, 8:16 p.m.
PD Predicate disambiguation batch_69f72a00c5f081908b6539d15baf4e12 completed May 3, 2026, 10:57 a.m.
Created at: April 27, 2026, 4:16 a.m.