Triple

T6810195
Position Surface form Disambiguated ID Type / Status
Subject Gyeryongsan E156609 entity
Predicate hasTemple P1191 FINISHED
Object Gapsa
Gapsa is an ancient Buddhist temple in South Korea, renowned as one of the principal temples on Mount Gyeryong.
 E620510 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: Gapsa | Statement: [Gyeryongsan, hasTemple, Gapsa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gapsa
Context triple: [Gyeryongsan, hasTemple, Gapsa]
  • A. Gardein
    Gardein is a plant-based food brand known for its wide range of meatless products such as chicken, beef, and fish alternatives made from soy, wheat, and pea proteins.
  • B. Golus
    Golus is a Yiddish term referring to the Jewish exile and dispersion from their ancestral homeland, encompassing both the physical diaspora and its spiritual-historical implications.
  • C. Gharaunda
    Gharaunda is a town in the Indian state of Haryana known for its agricultural market and proximity to the historic city of Karnal.
  • D. Gouderak
    Gouderak is a small village in the Dutch province of South Holland, situated along the Hollandse IJssel river.
  • E. Golo
    Golo is a masculine given name most notably borne by the German historian and essayist Golo Mann.
  • 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: Gapsa
Triple: [Gyeryongsan, hasTemple, Gapsa]
Generated description
Gapsa is an ancient Buddhist temple in South Korea, renowned as one of the principal temples on Mount Gyeryong.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gapsa
Target entity description: Gapsa is an ancient Buddhist temple in South Korea, renowned as one of the principal temples on Mount Gyeryong.
  • A. Gardein
    Gardein is a plant-based food brand known for its wide range of meatless products such as chicken, beef, and fish alternatives made from soy, wheat, and pea proteins.
  • B. Golus
    Golus is a Yiddish term referring to the Jewish exile and dispersion from their ancestral homeland, encompassing both the physical diaspora and its spiritual-historical implications.
  • C. Gharaunda
    Gharaunda is a town in the Indian state of Haryana known for its agricultural market and proximity to the historic city of Karnal.
  • D. Gouderak
    Gouderak is a small village in the Dutch province of South Holland, situated along the Hollandse IJssel river.
  • E. Golo
    Golo is a masculine given name most notably borne by the German historian and essayist Golo Mann.
  • 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_69c68828b26c819090fe9df7612bbc27 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d30ded6481908fd64611607c610e completed March 27, 2026, 6:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c71aa7dc3c81909ef422b5c51ae6be completed March 28, 2026, 12:02 a.m.
NEDg Description generation batch_69c71e7cd6448190845888760c677eda completed March 28, 2026, 12:19 a.m.
NED2 Entity disambiguation (via description) batch_69c71edd37048190bf4de088ad9f11de completed March 28, 2026, 12:20 a.m.
Created at: March 27, 2026, 2:16 p.m.