Triple

T3821240
Position Surface form Disambiguated ID Type / Status
Subject Atta cephalotes E84376 entity
Predicate genus P87 FINISHED
Object Atta
Atta is a genus of New World leafcutter ants known for their complex social colonies and large-scale fungus farming using freshly cut plant material.
 E391901 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: Atta | Statement: [Atta cephalotes, genus, Atta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Atta
Context triple: [Atta cephalotes, genus, Atta]
  • A. Ate
    Ate is a populous district in the eastern part of Lima, Peru, known for its mix of industrial zones, residential areas, and growing commercial activity.
  • B. Agta
    The Agta are an indigenous Negrito people of the Philippines known for their traditionally nomadic, forest-based lifestyle and rich oral traditions.
  • C. Arbela
    Arbela is the ancient name of the modern city of Erbil in Iraqi Kurdistan, historically known as a major Assyrian and later Hellenistic center near the site of Alexander the Great’s victory at the Battle of Gaugamela.
  • D. Attai
    Attai is a minor biblical figure mentioned in the Old Testament as a descendant in the royal line of Judah.
  • E. Banna
    Banna is the Latin name of Birdoswald Roman Fort, a key military site along Hadrian’s Wall in Roman Britain.
  • 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: Atta
Triple: [Atta cephalotes, genus, Atta]
Generated description
Atta is a genus of New World leafcutter ants known for their complex social colonies and large-scale fungus farming using freshly cut plant material.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Atta
Target entity description: Atta is a genus of New World leafcutter ants known for their complex social colonies and large-scale fungus farming using freshly cut plant material.
  • A. Ate
    Ate is a populous district in the eastern part of Lima, Peru, known for its mix of industrial zones, residential areas, and growing commercial activity.
  • B. Agta
    The Agta are an indigenous Negrito people of the Philippines known for their traditionally nomadic, forest-based lifestyle and rich oral traditions.
  • C. Arbela
    Arbela is the ancient name of the modern city of Erbil in Iraqi Kurdistan, historically known as a major Assyrian and later Hellenistic center near the site of Alexander the Great’s victory at the Battle of Gaugamela.
  • D. Attai
    Attai is a minor biblical figure mentioned in the Old Testament as a descendant in the royal line of Judah.
  • E. Banna
    Banna is the Latin name of Birdoswald Roman Fort, a key military site along Hadrian’s Wall in Roman Britain.
  • 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_69aed931f5908190be2c07af66d4df25 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeea61a63c819086e16b89d2ea2157 completed March 9, 2026, 3:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb4998248190b4174dd80a8e790c completed March 14, 2026, 6:08 a.m.
NEDg Description generation batch_69b4ffcf7e24819098cf2e46b92bed4a completed March 14, 2026, 6:27 a.m.
NED2 Entity disambiguation (via description) batch_69b500596e308190a31e44c24de3f31d completed March 14, 2026, 6:29 a.m.
Created at: March 9, 2026, 3:17 p.m.