Triple

T8184964
Position Surface form Disambiguated ID Type / Status
Subject Procellariidae E191158 entity
Predicate containsTaxon P9413 FINISHED
Object Thalassoica
Thalassoica is a small genus of Antarctic seabirds in the petrel family, known for species such as the Antarctic petrel that breed on polar coasts and islands.
E716821 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: Thalassoica | Statement: [Procellariidae, containsTaxon, Thalassoica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thalassoica
Context triple: [Procellariidae, containsTaxon, Thalassoica]
  • A. Struthidea
    Struthidea is a genus of Australian passerine birds in the mud-nest builder family Corcoracidae, best known for the apostlebird.
  • B. Corthylio
    Corthylio is a genus of small passerine birds in the kinglet family Regulidae, best known for the ruby-crowned kinglet.
  • C. Psarocolius
    Psarocolius is a genus of large, tropical New World orioles known as oropendolas, characterized by their long tails, hanging woven nests, and loud, gurgling calls.
  • D. Aloisia
    Aloisia is a feminine given name, used as an alternative spelling of Aloysia and related to names like Aloysius and Louise.
  • E. Pooecetes
    Pooecetes is a small genus of New World sparrows in the family Passerellidae, best known for the Vesper Sparrow.
  • 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: Thalassoica
Triple: [Procellariidae, containsTaxon, Thalassoica]
Generated description
Thalassoica is a small genus of Antarctic seabirds in the petrel family, known for species such as the Antarctic petrel that breed on polar coasts and islands.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Thalassoica
Target entity description: Thalassoica is a small genus of Antarctic seabirds in the petrel family, known for species such as the Antarctic petrel that breed on polar coasts and islands.
  • A. Struthidea
    Struthidea is a genus of Australian passerine birds in the mud-nest builder family Corcoracidae, best known for the apostlebird.
  • B. Corthylio
    Corthylio is a genus of small passerine birds in the kinglet family Regulidae, best known for the ruby-crowned kinglet.
  • C. Psarocolius
    Psarocolius is a genus of large, tropical New World orioles known as oropendolas, characterized by their long tails, hanging woven nests, and loud, gurgling calls.
  • D. Aloisia
    Aloisia is a feminine given name, used as an alternative spelling of Aloysia and related to names like Aloysius and Louise.
  • E. Pooecetes
    Pooecetes is a small genus of New World sparrows in the family Passerellidae, best known for the Vesper Sparrow.
  • 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_69ca82c4538081909404325aa5639483 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4c507f248190b599b4a629b7518a completed March 31, 2026, 4:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccbf95fd5c81908391dc160723b9e9 completed April 1, 2026, 6:47 a.m.
NEDg Description generation batch_69ccc315c73c81908ba65073c5eab6e1 completed April 1, 2026, 7:02 a.m.
NED2 Entity disambiguation (via description) batch_69ccd87585148190a2d8b81ab352d123 completed April 1, 2026, 8:33 a.m.
Created at: March 30, 2026, 5:41 p.m.