Triple

T11557528
Position Surface form Disambiguated ID Type / Status
Subject Marcus Annaeus Mela E274053 entity
Predicate cognomen P6662 FINISHED
Object Mela
Mela is the cognomen of Marcus Annaeus Mela, a Roman from the prominent Annaei family and father of the philosopher and statesman Lucan.
E932965 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: Mela | Statement: [Marcus Annaeus Mela, cognomen, Mela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mela
Context triple: [Marcus Annaeus Mela, cognomen, Mela]
  • A. Mella
    Mella is a Spanish-language surname most notably associated with Cuban revolutionary leader Julio Antonio Mella.
  • B. Meket
    Meket was an ancient Egyptian queen consort of the 11th Dynasty pharaoh Mentuhotep II.
  • C. Manzala
    Manzala is a town in northeastern Egypt situated near Lake Manzala and known for its fishing and agricultural activities.
  • D. Marcali
    Marcali is a small town in southwestern Hungary known for its agricultural surroundings and role as a local administrative and service center in Somogy County.
  • E. Malayer
    Malayer is a major city in western Iran known for its traditional handicrafts, particularly carpet weaving and woodcarving, and its role as an economic and cultural center in Hamedan Province.
  • 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: Mela
Triple: [Marcus Annaeus Mela, cognomen, Mela]
Generated description
Mela is the cognomen of Marcus Annaeus Mela, a Roman from the prominent Annaei family and father of the philosopher and statesman Lucan.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mela
Target entity description: Mela is the cognomen of Marcus Annaeus Mela, a Roman from the prominent Annaei family and father of the philosopher and statesman Lucan.
  • A. Mella
    Mella is a Spanish-language surname most notably associated with Cuban revolutionary leader Julio Antonio Mella.
  • B. Meket
    Meket was an ancient Egyptian queen consort of the 11th Dynasty pharaoh Mentuhotep II.
  • C. Manzala
    Manzala is a town in northeastern Egypt situated near Lake Manzala and known for its fishing and agricultural activities.
  • D. Marcali
    Marcali is a small town in southwestern Hungary known for its agricultural surroundings and role as a local administrative and service center in Somogy County.
  • E. Malayer
    Malayer is a major city in western Iran known for its traditional handicrafts, particularly carpet weaving and woodcarving, and its role as an economic and cultural center in Hamedan Province.
  • 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_69d6aae4dfa48190a3ab0b19a159a3c5 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d88a888e8481909386009b9603e4d3 completed April 10, 2026, 5:28 a.m.
NED1 Entity disambiguation (via context triple) batch_69e6e87953088190b72d0afeb9251535 completed April 21, 2026, 3:01 a.m.
NEDg Description generation batch_69e6ef93e7d88190af3853b82de23c1b completed April 21, 2026, 3:31 a.m.
NED2 Entity disambiguation (via description) batch_69e6f9144afc819081ee7f78e32ad39a completed April 21, 2026, 4:12 a.m.
Created at: April 8, 2026, 9:37 p.m.