Triple

T24123595
Position Surface form Disambiguated ID Type / Status
Subject Gyeongju Kim clan E597729 entity
Predicate hasBonGwanInHangul P154937 FINISHED
Object 경주
경주 is a historic city in South Korea’s North Gyeongsang Province, famed as the former capital of the ancient Silla Kingdom and home to numerous UNESCO World Heritage sites.
 E1615399 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: 경주 | Statement: [Gyeongju Kim clan, hasBonGwanInHangul, 경주]
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: 경주
Triple: [Gyeongju Kim clan, hasBonGwanInHangul, 경주]
Generated description
경주 is a historic city in South Korea’s North Gyeongsang Province, famed as the former capital of the ancient Silla Kingdom and home to numerous UNESCO World Heritage sites.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasBonGwanInHangul
Context triple: [Gyeongju Kim clan, hasBonGwanInHangul, 경주]
  • A. hasHangulName
    Indicates that an entity is associated with a name written in the Korean Hangul script.
  • B. hanjaName
    Indicates that one entity is the Sino-Korean (hanja) written form corresponding to the name of another entity.
  • C. hangulNameRomanized
    Indicates that an entity’s Korean Hangul name is represented in its romanized (Latin alphabet) form.
  • D. koreanReadingHangul
    Indicates that an entity’s Korean reading is represented in Hangul script.
  • E. hasKoreanVersion
    Indicates that something has a corresponding version or counterpart that is in the Korean language.
  • F. None of above. chosen

Provenance (7 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_69e288c808b881909fed7d18f04bcbbe completed April 17, 2026, 7:23 p.m.
NER Named-entity recognition batch_69f1dee718f88190860d40c6f09a77c8 completed April 29, 2026, 10:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0f969177408190aaf66a4daeb25e52 completed May 21, 2026, 11:34 p.m.
NEDg Description generation batch_6a0f96e1bccc8190a270f490d167483d completed May 21, 2026, 11:36 p.m.
NED2 Entity disambiguation (via description) batch_6a0f98194640819086e65f85bb0bede1 completed May 21, 2026, 11:41 p.m.
PD Predicate disambiguation batch_69f1765650fc8190a6bc1eb512b240bf completed April 29, 2026, 3:09 a.m.
PDg Predicate description generation batch_69f17c28b684819084eea522126463f8 completed April 29, 2026, 3:34 a.m.
Created at: April 17, 2026, 11:06 p.m.