Triple

T3165753
Position Surface form Disambiguated ID Type / Status
Subject Matthias Castrén E66206 entity
Predicate studied P778 FINISHED
Object Tungusic languages E62256 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: Tungusic languages | Statement: [Matthias Castrén, studied, Tungusic languages]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tungusic languages
Context triple: [Matthias Castrén, studied, Tungusic languages]
  • A. Tungusic languages chosen
    Tungusic languages are a family of languages spoken in eastern Siberia, northeastern China, and parts of the Russian Far East, including languages such as Evenki and Manchu.
  • B. Mongolic languages
    Mongolic languages are a family of closely related languages spoken primarily in Mongolia, northern China, and parts of Russia, including the major language Mongolian.
  • C. Karluk languages
    Karluk languages are a subgroup of the Turkic language family that includes major Central Asian languages such as Uzbek and Uyghur.
  • D. Lakkia–Biao languages
    The Lakkia–Biao languages are a small branch of the Tai–Kadai language family spoken by minority communities in southern China, notable for preserving archaic features distinct from the more widespread Tai languages.
  • E. Transeurasian languages
    Transeurasian languages are a proposed macro-family of languages stretching from Eastern Europe across Siberia to East Asia, hypothesized to include Turkic, Mongolic, Tungusic, Koreanic, and Japonic.
  • 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_69ad8585d7988190af37365331093ccd completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada6424ee48190a29891ffbbc3811d completed March 8, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24b552b488190938ed9fe4d046b01 completed March 12, 2026, 5:12 a.m.
Created at: March 8, 2026, 3:06 p.m.