Triple

T9955983
Position Surface form Disambiguated ID Type / Status
Subject Caecilia Attica E195446 entity
Predicate mother P120 FINISHED
Object Pilia
Pilia was a Roman woman of the late Republic, known primarily as the wife of Marcus Atius Balbus and mother-in-law of Julius Caesar’s sister Julia.
 E831872 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: Pilia | Statement: [Caecilia Attica, mother, Pilia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pilia
Context triple: [Caecilia Attica, mother, Pilia]
  • A. Palaonda
    Palaonda is an indoor ice arena in Bolzano, Italy, primarily used for ice hockey and other sporting and entertainment events.
  • B. Pilla
    Pilla is an Italian surname most notably associated with Franca Pilla, the wife of former Italian President Carlo Azeglio Ciampi.
  • C. Taroa
    Taroa is the main settlement and administrative center of Maloelap Atoll in the Marshall Islands, known historically for its World War II-era Japanese airbase.
  • D. Pilcaniyeu
    Pilcaniyeu is a small town in Argentina’s Patagonia region, located in the Andean area of Río Negro Province and known for its rural character and nearby natural landscapes.
  • E. Mawanella
    Mawanella is a town in central Sri Lanka known as a key transit point on the Colombo–Kandy road and for its surrounding rubber and tea plantations.
  • 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: Pilia
Triple: [Caecilia Attica, mother, Pilia]
Generated description
Pilia was a Roman woman of the late Republic, known primarily as the wife of Marcus Atius Balbus and mother-in-law of Julius Caesar’s sister Julia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pilia
Target entity description: Pilia was a Roman woman of the late Republic, known primarily as the wife of Marcus Atius Balbus and mother-in-law of Julius Caesar’s sister Julia.
  • A. Palaonda
    Palaonda is an indoor ice arena in Bolzano, Italy, primarily used for ice hockey and other sporting and entertainment events.
  • B. Pilla
    Pilla is an Italian surname most notably associated with Franca Pilla, the wife of former Italian President Carlo Azeglio Ciampi.
  • C. Taroa
    Taroa is the main settlement and administrative center of Maloelap Atoll in the Marshall Islands, known historically for its World War II-era Japanese airbase.
  • D. Pilcaniyeu
    Pilcaniyeu is a small town in Argentina’s Patagonia region, located in the Andean area of Río Negro Province and known for its rural character and nearby natural landscapes.
  • E. Mawanella
    Mawanella is a town in central Sri Lanka known as a key transit point on the Colombo–Kandy road and for its surrounding rubber and tea plantations.
  • 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_69ca82eaaa008190a54fa1a9f954b9ad completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cdb6976b50819097a0ae347354e92c completed April 2, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69d23d71342081908084c27790ef4fcc completed April 5, 2026, 10:46 a.m.
NEDg Description generation batch_69d23fb02c6081909f2c99ca21c90822 completed April 5, 2026, 10:55 a.m.
NED2 Entity disambiguation (via description) batch_69d24047ae4081909678ca9cf6cfbfff completed April 5, 2026, 10:58 a.m.
Created at: March 30, 2026, 8:46 p.m.