Triple

T7641500
Position Surface form Disambiguated ID Type / Status
Subject Samma dynasty E173019 entity
Predicate currency P245 FINISHED
Object tanka E68261 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: tanka | Statement: [Samma dynasty, currency, tanka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: tanka
Context triple: [Samma dynasty, currency, tanka]
  • A. tanka chosen
    The tanka was a medieval silver coin that served as a standard monetary unit across much of the Indian subcontinent under various Islamic and later dynasties.
  • B. Haiku
    Haiku is an open-source, lightweight desktop operating system inspired by BeOS, designed for speed, simplicity, and consistency.
  • C. Temwaiku
    Temwaiku is a village and district within South Tarawa in Kiribati, known as one of the populated islets forming the country's capital area.
  • D. Tanka people
    The Tanka people are a traditionally boat-dwelling ethnic subgroup in southern China, especially in the coastal and river regions of Guangdong and nearby areas, known for their distinct maritime culture and customs.
  • E. Haikasoru
    Haikasoru is a publishing imprint of Viz Media that specializes in translating and releasing Japanese science fiction and fantasy novels in English.
  • 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_69c6995360188190968ee57b72a1627f completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c6facefbe08190882bd76cf3cd605e completed March 27, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c870cd11648190b9aeedadb7bc1981 completed March 29, 2026, 12:22 a.m.
Created at: March 27, 2026, 3:57 p.m.