Triple

T17125040
Position Surface form Disambiguated ID Type / Status
Subject Dolichoderus E415571 entity
Predicate describedBy P264 FINISHED
Object Lund
Lund is a scientist and taxonomist known for formally describing species within the ant genus Dolichoderus.
E1263426 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: Lund | Statement: [Dolichoderus, describedBy, Lund]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lund
Context triple: [Dolichoderus, describedBy, Lund]
  • A. Lund
    Lund is a common Scandinavian surname of Swedish origin.
  • B. Lund
    Lund is a historic city in southern Sweden known for its medieval cathedral, prestigious university, and role as a significant cultural and academic center in Scandinavia.
  • C. Lund
    Lund is a district of the Norwegian city of Kristiansand, known for its residential areas, educational institutions, and proximity to the city center.
  • D. Lund
    Lund is a small unincorporated rural community located in Iron County, Utah, historically known as a railroad stop and gateway to nearby desert regions.
  • E. Lund
    Lund is a small municipality in Rogaland county in southwestern Norway, known for its rural landscapes and proximity to lakes and mountains.
  • 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: Lund
Triple: [Dolichoderus, describedBy, Lund]
Generated description
Lund is a scientist and taxonomist known for formally describing species within the ant genus Dolichoderus.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lund
Target entity description: Lund is a scientist and taxonomist known for formally describing species within the ant genus Dolichoderus.
  • A. Lund
    Lund is a common Scandinavian surname of Swedish origin.
  • B. Lund
    Lund is a historic city in southern Sweden known for its medieval cathedral, prestigious university, and role as a significant cultural and academic center in Scandinavia.
  • C. Lund
    Lund is a district of the Norwegian city of Kristiansand, known for its residential areas, educational institutions, and proximity to the city center.
  • D. Lund
    Lund is a small municipality in Rogaland county in southwestern Norway, known for its rural landscapes and proximity to lakes and mountains.
  • E. Lund
    Lund is a small unincorporated rural community located in Iron County, Utah, historically known as a railroad stop and gateway to nearby desert regions.
  • 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3f025fce481908e261f2e363e14f9 completed April 18, 2026, 8:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a018c36b32c8190a365b7b80207978c completed May 11, 2026, 7:58 a.m.
NEDg Description generation batch_6a018d86c7808190b9de682e49d4295c completed May 11, 2026, 8:04 a.m.
NED2 Entity disambiguation (via description) batch_6a018e57fa708190872ad2fb5f660507 completed May 11, 2026, 8:07 a.m.
Created at: April 10, 2026, 5:36 a.m.