Triple

T8301370
Position Surface form Disambiguated ID Type / Status
Subject Chinese Wikinews E194355 entity
Predicate hasSisterProject P14971 FINISHED
Object Chinese Wikisource E724592 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: Chinese Wikisource | Statement: [Chinese Wikinews, hasSisterProject, Chinese Wikisource]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chinese Wikisource
Context triple: [Chinese Wikinews, hasSisterProject, Chinese Wikisource]
  • A. Chinese Wikisource chosen
    Chinese Wikisource is the Chinese-language edition of Wikisource, a free online digital library of public domain and freely licensed texts.
  • B. Chinese Wikibooks
    Chinese Wikibooks is the Chinese-language edition of Wikibooks, a Wikimedia project that hosts free, collaboratively written open-content textbooks and instructional materials.
  • C. Korean Wikisource
    Korean Wikisource is the Korean-language edition of Wikisource, a Wikimedia project that provides a free online library of public domain and freely licensed texts in Korean.
  • D. Japanese Wikisource
    Japanese Wikisource is the Japanese-language edition of Wikisource, a free online digital library of public domain and freely licensed texts.
  • E. Vietnamese Wikisource
    Vietnamese Wikisource is the Vietnamese-language edition of Wikisource, a free online digital library of public domain and freely licensed texts.
  • 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_69ca82e50ebc81909aa7b260c76bd757 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7e891030819097f4a26992a8b469 completed March 31, 2026, 7:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd953b5fd881909696eb2647dc5f92 completed April 1, 2026, 9:59 p.m.
Created at: March 30, 2026, 5:53 p.m.