Triple

T8898157
Position Surface form Disambiguated ID Type / Status
Subject Nesospiza E211856 entity
Predicate taxonAuthor P7386 FINISHED
Object Cabanis
Cabanis was a 19th-century German ornithologist known for describing numerous bird taxa and contributing significantly to avian systematics.
 E764939 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: Cabanis | Statement: [Nesospiza, taxonAuthor, Cabanis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Cabanis
Context triple: [Nesospiza, taxonAuthor, Cabanis]
  • A. Marcelin
    Marcelin is a French diminutive form of the given name Marcel, often used as an affectionate or familiar variant.
  • B. Boissière
    Boissière is a Paris Métro station on the city’s Right Bank, located in the 16th arrondissement near the Trocadéro area.
  • C. Lebrun
    Lebrun is a French surname borne by various notable figures in politics, arts, and other fields.
  • D. Dolomieu
    Dolomieu is a commune in the Isère department of southeastern France, known as the birthplace of mathematician Élie Cartan.
  • E. Mansois
    Mansois is a local name for the red wine grape variety Fer Servadou, traditionally used in the wines of southwest France.
  • 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: Cabanis
Triple: [Nesospiza, taxonAuthor, Cabanis]
Generated description
Cabanis was a 19th-century German ornithologist known for describing numerous bird taxa and contributing significantly to avian systematics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Cabanis
Target entity description: Cabanis was a 19th-century German ornithologist known for describing numerous bird taxa and contributing significantly to avian systematics.
  • A. Marcelin
    Marcelin is a French diminutive form of the given name Marcel, often used as an affectionate or familiar variant.
  • B. Boissière
    Boissière is a Paris Métro station on the city’s Right Bank, located in the 16th arrondissement near the Trocadéro area.
  • C. Lebrun
    Lebrun is a French surname borne by various notable figures in politics, arts, and other fields.
  • D. Dolomieu
    Dolomieu is a commune in the Isère department of southeastern France, known as the birthplace of mathematician Élie Cartan.
  • E. Mansois
    Mansois is a local name for the red wine grape variety Fer Servadou, traditionally used in the wines of southwest France.
  • 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_69ca83918d3081909b326fa3750cb8c8 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc642618908190b3df50cbbabff93d completed April 1, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfac093034819085d8fb1832ec5d73 completed April 3, 2026, 12:01 p.m.
NEDg Description generation batch_69cfacb58f208190b5e8eeba58f1bd78 completed April 3, 2026, 12:04 p.m.
NED2 Entity disambiguation (via description) batch_69cfad6fff348190b0491ba38d2e6ce5 completed April 3, 2026, 12:07 p.m.
Created at: March 30, 2026, 6:54 p.m.