Triple

T14979906
Position Surface form Disambiguated ID Type / Status
Subject Britannicus E373546 entity
Predicate allegedKiller P41279 FINISHED
Object Locusta
Locusta was a notorious Roman poisoner of the 1st century AD, infamous for her role in high-profile political murders under Emperor Nero.
 E1130804 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: Locusta | Statement: [Britannicus, allegedKiller, Locusta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Locusta
Context triple: [Britannicus, allegedKiller, Locusta]
  • A. Tisbe
    Tisbe is one of the wicked stepsisters in Gioachino Rossini’s opera "La Cenerentola," known for her comic vanity and rivalry with her sister Clorinda.
  • B. Sciarra
    Sciarra is an Italian given name historically associated with the noble Colonna family, notably the medieval nobleman Sciarra Colonna.
  • C. Boidobra
    Boidobra is a civil parish located in the municipality of Covilhã in central Portugal.
  • D. Paratus
    Paratus is the Latin motto of Bentley University, meaning "prepared" and reflecting the institution’s emphasis on readiness for professional and personal success.
  • E. Telchinia
    Telchinia is the ancient name of the Greek city-state later known as Sicyon, located in the northern Peloponnese.
  • 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: Locusta
Triple: [Britannicus, allegedKiller, Locusta]
Generated description
Locusta was a notorious Roman poisoner of the 1st century AD, infamous for her role in high-profile political murders under Emperor Nero.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Locusta
Target entity description: Locusta was a notorious Roman poisoner of the 1st century AD, infamous for her role in high-profile political murders under Emperor Nero.
  • A. Tisbe
    Tisbe is one of the wicked stepsisters in Gioachino Rossini’s opera "La Cenerentola," known for her comic vanity and rivalry with her sister Clorinda.
  • B. Sciarra
    Sciarra is an Italian given name historically associated with the noble Colonna family, notably the medieval nobleman Sciarra Colonna.
  • C. Boidobra
    Boidobra is a civil parish located in the municipality of Covilhã in central Portugal.
  • D. Paratus
    Paratus is the Latin motto of Bentley University, meaning "prepared" and reflecting the institution’s emphasis on readiness for professional and personal success.
  • E. Telchinia
    Telchinia is the ancient name of the Greek city-state later known as Sicyon, located in the northern Peloponnese.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6fcebf481909f72cab577560d82 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8bef015c8190bdfb1b9144b2a55c completed May 9, 2026, 1:20 a.m.
NEDg Description generation batch_69fe8fec76848190b83c6399aaacda76 completed May 9, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69fe9090d23c8190b8a90e8ad8dacade completed May 9, 2026, 1:40 a.m.
Created at: April 10, 2026, 2:51 a.m.