Triple

T3357181
Position Surface form Disambiguated ID Type / Status
Subject leopard seal E70632 entity
Predicate class P87 FINISHED
Object Mammalia E145943 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: Mammalia | Statement: [leopard seal, class, Mammalia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mammalia
Context triple: [leopard seal, class, Mammalia]
  • A. Mammalia chosen
    Mammalia is the vertebrate class of warm-blooded, typically fur-bearing animals that nourish their young with milk produced by mammary glands.
  • B. Theria
    Theria is a major subclass of mammals that includes all live-bearing species such as marsupials and placental mammals, excluding egg-laying monotremes.
  • C. Eutheria
    Eutheria is a major clade of mammals that includes all placental mammals and their extinct relatives, characterized by prolonged gestation and complex placental development.
  • D. Marsupialia
    Marsupialia is a group of mammals characterized by giving birth to relatively undeveloped young that typically continue developing in a pouch.
  • E. Carnivora
    Carnivora is a diverse order of primarily meat-eating mammals that includes families such as bears, cats, dogs, weasels, and seals.
  • 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_69ad85a660c48190998489309a3b4869 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb244435c81908e35d2aa36ec4f46 completed March 8, 2026, 5:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bbbc3a48190bc17572ba3136948 completed March 12, 2026, 11:26 p.m.
Created at: March 8, 2026, 3:13 p.m.