Triple

T12355921
Position Surface form Disambiguated ID Type / Status
Subject Rana E294611 entity
Predicate includesSpecies P10920 FINISHED
Object Rana zhengi
Rana zhengi is a species of true frog in the genus Rana, native to parts of East Asia and typically associated with freshwater habitats.
 E1023143 NE FINISHED

How this triple was built (4 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: Rana zhengi | Statement: [Rana, includesSpecies, Rana zhengi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rana zhengi
Context triple: [Rana, includesSpecies, Rana zhengi]
  • A. Rana tagoi
    Rana tagoi is a species of true frog native to East Asia, particularly Japan, known for inhabiting cool, fast-flowing mountain streams.
  • B. Rana uenoi
    Rana uenoi is a species of true frog in the genus Rana, native to parts of East Asia and typically associated with freshwater habitats.
  • C. Rana chensinensis
    Rana chensinensis is a species of true frog native to East Asia, particularly China, known for inhabiting cold, high-altitude freshwater environments.
  • D. Rana tsushimensis
    Rana tsushimensis is a species of true frog endemic to Tsushima Island in Japan, known for inhabiting streams and forested wetlands.
  • E. Rana kukunoris
    Rana kukunoris is a species of true frog native to high-altitude regions of the Tibetan Plateau in China.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Rana zhengi
Triple: [Rana, includesSpecies, Rana zhengi]
Generated description
Rana zhengi is a species of true frog in the genus Rana, native to parts of East Asia and typically associated with freshwater habitats.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rana zhengi
Target entity description: Rana zhengi is a species of true frog in the genus Rana, native to parts of East Asia and typically associated with freshwater habitats.
  • A. Rana tagoi
    Rana tagoi is a species of true frog native to East Asia, particularly Japan, known for inhabiting cool, fast-flowing mountain streams.
  • B. Rana uenoi
    Rana uenoi is a species of true frog in the genus Rana, native to parts of East Asia and typically associated with freshwater habitats.
  • C. Rana chensinensis
    Rana chensinensis is a species of true frog native to East Asia, particularly China, known for inhabiting cold, high-altitude freshwater environments.
  • D. Rana tsushimensis
    Rana tsushimensis is a species of true frog endemic to Tsushima Island in Japan, known for inhabiting streams and forested wetlands.
  • E. Rana kukunoris
    Rana kukunoris is a species of true frog native to high-altitude regions of the Tibetan Plateau in China.
  • F. None of above. chosen

Provenance (5 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_69d6ab6ccbec8190b09e2d357aa80064 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93f8bc60c8190b0ceb84093e70db4 completed April 10, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e256fe408190bd40b62eb51b6ef9 completed May 3, 2026, 5:51 a.m.
NEDg Description generation batch_69f6e62bfa4c8190ac8ae42a1a53f521 completed May 3, 2026, 6:07 a.m.
NED2 Entity disambiguation (via description) batch_69f6e6c30144819096acf6de7317d097 completed May 3, 2026, 6:10 a.m.
Created at: April 8, 2026, 9:54 p.m.