Triple

T3248087
Position Surface form Disambiguated ID Type / Status
Subject Vespasia Polla E68110 entity
Predicate cognomen P6662 FINISHED
Object Polla
Polla is an ancient Roman cognomen most notably borne by Vespasia Polla, the mother of Emperor Vespasian.
E340646 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: Polla | Statement: [Vespasia Polla, cognomen, Polla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Polla
Context triple: [Vespasia Polla, cognomen, Polla]
  • A. Polly
    Polly is a fictional character known as the daughter of Uncle Tom in Harriet Beecher Stowe’s novel "Uncle Tom’s Cabin."
  • B. Polly
    Polly is an LLVM project component that performs advanced loop optimizations and automatic parallelization using polyhedral compilation techniques.
  • C. Polly
    Polly is a ballad opera by John Gay, written as a sequel to his famous work "The Beggar's Opera" and noted for its satirical treatment of colonialism and morality.
  • D. Polly
    Polly is the nickname of Mary Prince, a West Indian woman whose 1831 autobiography was the first account of a Black woman’s life published in Britain and a powerful indictment of slavery.
  • E. Polow da Don
    Polow da Don is an American record producer and songwriter known for crafting hit hip-hop and R&B tracks for major artists in the 2000s and 2010s.
  • 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: Polla
Triple: [Vespasia Polla, cognomen, Polla]
Generated description
Polla is an ancient Roman cognomen most notably borne by Vespasia Polla, the mother of Emperor Vespasian.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Polla
Target entity description: Polla is an ancient Roman cognomen most notably borne by Vespasia Polla, the mother of Emperor Vespasian.
  • A. Polly
    Polly is a fictional character known as the daughter of Uncle Tom in Harriet Beecher Stowe’s novel "Uncle Tom’s Cabin."
  • B. Polly
    Polly is an LLVM project component that performs advanced loop optimizations and automatic parallelization using polyhedral compilation techniques.
  • C. Polly
    Polly is a ballad opera by John Gay, written as a sequel to his famous work "The Beggar's Opera" and noted for its satirical treatment of colonialism and morality.
  • D. Polly
    Polly is the nickname of Mary Prince, a West Indian woman whose 1831 autobiography was the first account of a Black woman’s life published in Britain and a powerful indictment of slavery.
  • E. Polow da Don
    Polow da Don is an American record producer and songwriter known for crafting hit hip-hop and R&B tracks for major artists in the 2000s and 2010s.
  • 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_69ad858e4c708190aa31d486cfee8a6a completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaf3e9ed0819096ac238098ac403c completed March 8, 2026, 5:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69b277639508819091390086a3c511d1 completed March 12, 2026, 8:20 a.m.
NEDg Description generation batch_69b2786c6bc88190bea732592426776d completed March 12, 2026, 8:25 a.m.
NED2 Entity disambiguation (via description) batch_69b27927308c81909c1dceb825eb1b81 completed March 12, 2026, 8:28 a.m.
Created at: March 8, 2026, 3:09 p.m.