Triple

T15022222
Position Surface form Disambiguated ID Type / Status
Subject Statilii E378113 entity
Predicate hasCognomen P6662 FINISHED
Object Lamprias
Lamprias is a Roman cognomen associated with members of the Statilii family in ancient Rome.
 E1134091 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: Lamprias | Statement: [Statilii, hasCognomen, Lamprias]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lamprias
Context triple: [Statilii, hasCognomen, Lamprias]
  • A. Selargius
    Selargius is a town in southern Sardinia, Italy, functioning largely as a residential suburb within the urban area of Cagliari.
  • B. Laeops
    Laeops is a genus of small, bottom-dwelling lefteye flounders found in marine waters of the Indo-Pacific region.
  • C. Lamproba
    Lamproba is a traditional Svan highland festival in Georgia marked by communal rituals, bonfires, and offerings that honor ancestors and seek blessings for the coming year.
  • D. Vromonas
    Vromonas is a small Greek island that forms part of the Echinades archipelago in the Ionian Sea.
  • E. Salamina
    Salamina is the main town and administrative center of Salamis Island in Greece, known for its coastal setting and role as the island’s primary hub of local life and services.
  • 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: Lamprias
Triple: [Statilii, hasCognomen, Lamprias]
Generated description
Lamprias is a Roman cognomen associated with members of the Statilii family in ancient Rome.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lamprias
Target entity description: Lamprias is a Roman cognomen associated with members of the Statilii family in ancient Rome.
  • A. Selargius
    Selargius is a town in southern Sardinia, Italy, functioning largely as a residential suburb within the urban area of Cagliari.
  • B. Laeops
    Laeops is a genus of small, bottom-dwelling lefteye flounders found in marine waters of the Indo-Pacific region.
  • C. Lamproba
    Lamproba is a traditional Svan highland festival in Georgia marked by communal rituals, bonfires, and offerings that honor ancestors and seek blessings for the coming year.
  • D. Vromonas
    Vromonas is a small Greek island that forms part of the Echinades archipelago in the Ionian Sea.
  • E. Salamina
    Salamina is the main town and administrative center of Salamis Island in Greece, known for its coastal setting and role as the island’s primary hub of local life and services.
  • 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_69d85cd3a3c881908c71fc424d459c17 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded765462c819097f331c9b39c80e3 completed April 15, 2026, 12:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dd2c96c8190a0368678584aaa16 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fea0c35b088190abf578ed016753cd completed May 9, 2026, 2:49 a.m.
NED2 Entity disambiguation (via description) batch_69fea16b16b8819080b31203189f8cfe completed May 9, 2026, 2:52 a.m.
Created at: April 10, 2026, 2:56 a.m.