Triple

T686950
Position Surface form Disambiguated ID Type / Status
Subject Yangtze River E13303 entity
Predicate formerNotableSpecies P965 FINISHED
Object Yangtze river dolphin (baiji)
The Yangtze river dolphin, or baiji, was a nearly blind freshwater dolphin endemic to China’s Yangtze River and is now considered functionally extinct due to habitat degradation and human activity.
E85260 NE FINISHED

How this triple was built (5 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: Yangtze river dolphin (baiji) | Statement: [Yangtze River, formerNotableSpecies, Yangtze river dolphin (baiji)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yangtze river dolphin (baiji)
Context triple: [Yangtze River, formerNotableSpecies, Yangtze river dolphin (baiji)]
  • A. Atlantic white-sided dolphin
    The Atlantic white-sided dolphin is a small, agile marine mammal found in the cold temperate waters of the North Atlantic Ocean, known for its striking black, white, and yellowish coloration and highly social behavior.
  • B. Sumatran rhinoceros
    The Sumatran rhinoceros is a critically endangered, small and hairy rhino species native to Southeast Asian forests, known as the most threatened of all living rhinoceroses.
  • C. West Indian manatee
    The West Indian manatee is a large, slow-moving, herbivorous marine mammal native to the warm coastal waters and rivers of the Caribbean and southeastern North America, where it is considered a vulnerable species.
  • D. Mediterranean monk seal
    The Mediterranean monk seal is one of the world’s most endangered marine mammals, a rare earless seal native to the Mediterranean and adjacent seas.
  • E. Naga
    Naga is a city in the Bicol Region of the Philippines known as a major religious, cultural, and commercial center, particularly famed for the annual Peñafrancia Festival.
  • 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: Yangtze river dolphin (baiji)
Triple: [Yangtze River, formerNotableSpecies, Yangtze river dolphin (baiji)]
Generated description
The Yangtze river dolphin, or baiji, was a nearly blind freshwater dolphin endemic to China’s Yangtze River and is now considered functionally extinct due to habitat degradation and human activity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Yangtze river dolphin (baiji)
Target entity description: The Yangtze river dolphin, or baiji, was a nearly blind freshwater dolphin endemic to China’s Yangtze River and is now considered functionally extinct due to habitat degradation and human activity.
  • A. Atlantic white-sided dolphin
    The Atlantic white-sided dolphin is a small, agile marine mammal found in the cold temperate waters of the North Atlantic Ocean, known for its striking black, white, and yellowish coloration and highly social behavior.
  • B. Sumatran rhinoceros
    The Sumatran rhinoceros is a critically endangered, small and hairy rhino species native to Southeast Asian forests, known as the most threatened of all living rhinoceroses.
  • C. West Indian manatee
    The West Indian manatee is a large, slow-moving, herbivorous marine mammal native to the warm coastal waters and rivers of the Caribbean and southeastern North America, where it is considered a vulnerable species.
  • D. Mediterranean monk seal
    The Mediterranean monk seal is one of the world’s most endangered marine mammals, a rare earless seal native to the Mediterranean and adjacent seas.
  • E. Naga
    Naga is a city in the Bicol Region of the Philippines known as a major religious, cultural, and commercial center, particularly famed for the annual Peñafrancia Festival.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: formerNotableSpecies
Context triple: [Yangtze River, formerNotableSpecies, Yangtze river dolphin (baiji)]
  • A. notableSpecies chosen
    Indicates that the subject is known for, or significantly associated with, the specified species.
  • B. featuresSpecies
    Indicates that something includes, presents, or highlights a particular species as part of its content or composition.
  • C. notableDomesticatedSpecies
    Indicates that the subject is a species that is particularly well-known or significant as a domesticated animal.
  • D. notableGenus
    Indicates that one entity is a genus that is especially prominent, well-known, or significant in relation to the other entity.
  • E. someSpeciesAre
    Indicates that at least one member of a specified group or category belongs to, or can be classified as, a particular species.
  • F. None of above.

Provenance (6 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a0f55f7481909e052a25bd12d455 completed March 1, 2026, 8:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5dca352248190a3e1b4e4c58a1e7f completed March 2, 2026, 6:53 p.m.
NEDg Description generation batch_69a5dd2e39808190ab116593299a94f8 completed March 2, 2026, 6:55 p.m.
NED2 Entity disambiguation (via description) batch_69a5fe3bb2a08190a01ce2ed8b52ee4a completed March 2, 2026, 9:16 p.m.
PD Predicate disambiguation batch_69a49d2048d48190ab99ab59accb6909 completed March 1, 2026, 8:10 p.m.
Created at: March 1, 2026, 7:36 p.m.