Triple

T10172560
Position Surface form Disambiguated ID Type / Status
Subject Annam E235365 entity
Predicate localName P657 FINISHED
Object Trung Kỳ E400828 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: Trung Kỳ | Statement: [Annam, localName, Trung Kỳ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Trung Kỳ
Context triple: [Annam, localName, Trung Kỳ]
  • A. Trung Kỳ chosen
    Trung Kỳ was the central region of Vietnam under French colonial administration, historically known as Annam.
  • B. Hòu Zhōu
    Hòu Zhōu was the Chinese dynasty known in English as the Later Zhou, one of the Five Dynasties that ruled northern China in the 10th century.
  • C. Mengu-Timur
    Mengu-Timur was a 13th-century khan of the Golden Horde, a division of the Mongol Empire that ruled over parts of Eastern Europe and the Eurasian steppe.
  • D. Old Hsiang
    Old Hsiang is an early historical form of the Xiang Chinese language, spoken in parts of Hunan province before later modern dialect developments.
  • E. Middelstum
    Middelstum is a historic village in the Dutch province of Groningen, known for its old churches and traditional architecture.
  • 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_69ca84ceafd0819085828600e11bed6b completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdec9f6dd8819081588600499165ee completed April 2, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d30101e3ec819095a587c0dae55f71 completed April 6, 2026, 12:40 a.m.
Created at: March 30, 2026, 9:10 p.m.