Triple

T19530853
Position Surface form Disambiguated ID Type / Status
Subject Ondol E488647 entity
Predicate alsoKnownAs P39 FINISHED
Object gudeul
Gudeul is a traditional Korean underfloor heating system that uses flues to channel heat beneath a room’s floor.
E1381476 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: gudeul | Statement: [Ondol, alsoKnownAs, gudeul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: gudeul
Context triple: [Ondol, alsoKnownAs, gudeul]
  • A. Gude
    Gude is an Afroasiatic Chadic language spoken primarily in parts of northeastern Nigeria and northern Cameroon.
  • B. Gukmun
    Gukmun is an old Korean term referring to the native Korean writing system that later came to be known as Joseongeul or Hangul.
  • C. Gukje Sijang
    Gukje Sijang is one of South Korea’s largest and most famous traditional markets, located in Busan and known for its wide variety of goods and bustling atmosphere.
  • D. Ghindae
    Ghindae is a town in Eritrea located within the Northern Red Sea administrative region.
  • E. Gugundhabe
    Gugundhabe is a Somali subclan within the larger Hawiye clan-family, traditionally associated with central and southern Somalia.
  • 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: gudeul
Triple: [Ondol, alsoKnownAs, gudeul]
Generated description
Gudeul is a traditional Korean underfloor heating system that uses flues to channel heat beneath a room’s floor.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: gudeul
Target entity description: Gudeul is a traditional Korean underfloor heating system that uses flues to channel heat beneath a room’s floor.
  • A. Gude
    Gude is an Afroasiatic Chadic language spoken primarily in parts of northeastern Nigeria and northern Cameroon.
  • B. Gukmun
    Gukmun is an old Korean term referring to the native Korean writing system that later came to be known as Joseongeul or Hangul.
  • C. Gukje Sijang
    Gukje Sijang is one of South Korea’s largest and most famous traditional markets, located in Busan and known for its wide variety of goods and bustling atmosphere.
  • D. Ghindae
    Ghindae is a town in Eritrea located within the Northern Red Sea administrative region.
  • E. Gugundhabe
    Gugundhabe is a Somali subclan within the larger Hawiye clan-family, traditionally associated with central and southern Somalia.
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363ec6cc8190b9e9ac0196b288f9 completed April 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a074e7b52d88190b0e095ce39d7a003 completed May 15, 2026, 4:48 p.m.
NEDg Description generation batch_6a074f6d79b88190a0b8442af2be0ed1 completed May 15, 2026, 4:53 p.m.
NED2 Entity disambiguation (via description) batch_6a074fed47bc8190b1a78dcc50345ca4 completed May 15, 2026, 4:55 p.m.
Created at: April 10, 2026, 1:41 p.m.