Triple

T20893034
Position Surface form Disambiguated ID Type / Status
Subject Tang E514455 entity
Predicate hasVariantTransliteration P5923 FINISHED
Object Tong NE NERFINISHED

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: Tong | Statement: [Tang, hasVariantTransliteration, Tong]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tong
Context triple: [Tang, hasVariantTransliteration, Tong]
  • A. Tʻang chosen
    Tʻang is the Wade–Giles romanization of the Chinese dynasty name commonly written as "Tang" in pinyin.
  • B. Tongging
    Tongging is a village in North Sumatra, Indonesia, known as a scenic gateway to Lake Toba and the nearby Sipiso-piso Waterfall.
  • C. Yuling
    Yuling is a given name most notably borne by Chinese table tennis player Zhu Yuling.
  • D. Tanglha
    Tanglha is a mountain range in the central Tibetan Plateau known for its high peaks and role as a watershed between major Asian river systems.
  • E. Taongi
    Taongi is a remote, uninhabited coral atoll in the Marshall Islands known for its rich marine biodiversity and relatively undisturbed natural environment.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d05fecd88190905a0ea80a24406a completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.