Triple

T7878007
Position Surface form Disambiguated ID Type / Status
Subject Hakka people E182904 entity
Predicate associatedWithArchitecture P2830 FINISHED
Object tulou
Tulou are large, fortified earthen communal buildings traditionally constructed by the Hakka people in rural southeastern China.
 E701624 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: tulou | Statement: [Hakka people, associatedWithArchitecture, tulou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: tulou
Context triple: [Hakka people, associatedWithArchitecture, tulou]
  • A. Tulak
    Tulak is a town in Afghanistan that serves as a local settlement within Ghor Province.
  • B. Tulunan
    Tulunan is a rural municipality in the province of North Cotabato on the island of Mindanao in the Philippines, known primarily for its agricultural economy.
  • C. Tilos
    Tilos is a small Greek island in the southeastern Aegean Sea, known for its unspoiled nature, rich biodiversity, and tranquil, less-touristed atmosphere.
  • D. Tiantangzhai
    Tiantangzhai is a prominent scenic mountain peak and nature reserve in central China, known for its rich biodiversity, forested landscapes, and status as a popular ecotourism destination.
  • E. Tebunginako
    Tebunginako is a village settlement on the atoll of Abaiang in the island nation of Kiribati, known for being severely affected by coastal erosion and sea-level rise.
  • 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: tulou
Triple: [Hakka people, associatedWithArchitecture, tulou]
Generated description
Tulou are large, fortified earthen communal buildings traditionally constructed by the Hakka people in rural southeastern China.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: tulou
Target entity description: Tulou are large, fortified earthen communal buildings traditionally constructed by the Hakka people in rural southeastern China.
  • A. Tulak
    Tulak is a town in Afghanistan that serves as a local settlement within Ghor Province.
  • B. Tulunan
    Tulunan is a rural municipality in the province of North Cotabato on the island of Mindanao in the Philippines, known primarily for its agricultural economy.
  • C. Tilos
    Tilos is a small Greek island in the southeastern Aegean Sea, known for its unspoiled nature, rich biodiversity, and tranquil, less-touristed atmosphere.
  • D. Tiantangzhai
    Tiantangzhai is a prominent scenic mountain peak and nature reserve in central China, known for its rich biodiversity, forested landscapes, and status as a popular ecotourism destination.
  • E. Tebunginako
    Tebunginako is a village settlement on the atoll of Abaiang in the island nation of Kiribati, known for being severely affected by coastal erosion and sea-level rise.
  • 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_69ca828a17248190b46defe758bc5ad3 completed March 30, 2026, 2:02 p.m.
NER Named-entity recognition batch_69cb39bd64e481909f699e7dd2818b8f completed March 31, 2026, 3:04 a.m.
NED1 Entity disambiguation (via context triple) batch_69cb5b7fef308190bbc74e13f4205192 completed March 31, 2026, 5:28 a.m.
NEDg Description generation batch_69cb7630b8908190a0b8f4856bceea0a completed March 31, 2026, 7:22 a.m.
NED2 Entity disambiguation (via description) batch_69cbbfb894588190971ade076acdbd5c completed March 31, 2026, 12:36 p.m.
Created at: March 30, 2026, 4:57 p.m.