Triple

T15352814
Position Surface form Disambiguated ID Type / Status
Subject Jinci Temple E367094 entity
Predicate hasAlternativeName P39 FINISHED
Object Jinci
Jinci is an ancient temple complex near Taiyuan in Shanxi, China, renowned for its historic architecture, sacred springs, and richly decorated wooden halls.
E1152191 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: Jinci | Statement: [Jinci Temple, hasAlternativeName, Jinci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jinci
Context triple: [Jinci Temple, hasAlternativeName, Jinci]
  • A. Jínova
    Jínova is a municipal district within the municipality of San Juan de la Maguana in the San Juan Province of the Dominican Republic.
  • B. Koji
    Koji is a Japanese given name commonly associated with notable figures in entertainment, sports, and the arts.
  • C. Jasaq
    Jasaq is an alternative name for Yassa, the traditional legal code and set of decrees historically attributed to Genghis Khan in the Mongol Empire.
  • D. Sjenica
    Sjenica is a town in southwestern Serbia known for its harsh winters, high-altitude plateau setting, and production of the famous Sjenica cheese.
  • E. Jaga
    Jaga is the popular nickname of Jagiellonia Białystok, a professional football club based in Białystok, Poland.
  • 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: Jinci
Triple: [Jinci Temple, hasAlternativeName, Jinci]
Generated description
Jinci is an ancient temple complex near Taiyuan in Shanxi, China, renowned for its historic architecture, sacred springs, and richly decorated wooden halls.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jinci
Target entity description: Jinci is an ancient temple complex near Taiyuan in Shanxi, China, renowned for its historic architecture, sacred springs, and richly decorated wooden halls.
  • A. Jínova
    Jínova is a municipal district within the municipality of San Juan de la Maguana in the San Juan Province of the Dominican Republic.
  • B. Koji
    Koji is a Japanese given name commonly associated with notable figures in entertainment, sports, and the arts.
  • C. Jasaq
    Jasaq is an alternative name for Yassa, the traditional legal code and set of decrees historically attributed to Genghis Khan in the Mongol Empire.
  • D. Sjenica
    Sjenica is a town in southwestern Serbia known for its harsh winters, high-altitude plateau setting, and production of the famous Sjenica cheese.
  • E. Jaga
    Jaga is the popular nickname of Jagiellonia Białystok, a professional football club based in Białystok, Poland.
  • 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e2a8e88819093e4b7479b2c80cd completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01fd53688190939787a3d6ff3bb9 completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff030970588190a793cd710e819635 completed May 9, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69ff04633de08190867ad3baec6b2b02 completed May 9, 2026, 9:54 a.m.
Created at: April 10, 2026, 3:17 a.m.