Triple

T6263158
Position Surface form Disambiguated ID Type / Status
Subject Humen E140348 entity
Predicate hasStructure P35 FINISHED
Object Humen Forts E579841 NE FINISHED

How this triple was built (2 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: Humen Forts | Statement: [Humen, hasStructure, Humen Forts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Humen Forts
Context triple: [Humen, hasStructure, Humen Forts]
  • A. Humen Forts chosen
    Humen Forts are a historic coastal defense complex in Guangdong, China, best known for their role in guarding the Pearl River estuary and in battles during the Opium Wars.
  • B. Kankwari Fort
    Kankwari Fort is a historic hilltop fortress in Rajasthan, India, known for its scenic views and association with Mughal-era history, located within the Sariska Tiger Reserve.
  • C. Fort Zeelandia
    Fort Zeelandia is a historic 17th-century Dutch colonial fortress in Paramaribo, Suriname, that played a central role in the city’s military and administrative history.
  • D. Kalyangad Fort
    Kalyangad Fort is a historic hill fort in Maharashtra, India, known for its strategic location near Satara and its role in the Maratha era.
  • E. Fort Denison
    Fort Denison is a historic former penal site and defensive fortification located on a small island in Sydney Harbour, Australia.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c008c95c5c819084bd3dd56133d84d completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06387fec0819095b47a37b9402aa9 completed March 22, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c51932e704819083e1ed17a86f6b5e completed March 26, 2026, 11:32 a.m.
Created at: March 22, 2026, 4:25 p.m.