Triple

T3643033
Position Surface form Disambiguated ID Type / Status
Subject Heraclius E77233 entity
Predicate spouse P13 FINISHED
Object Martina
Martina was a Byzantine empress and the second wife of Emperor Heraclius, known for her controversial influence at court and her role in the empire’s turbulent 7th-century politics.
E375082 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: Martina | Statement: [Heraclius, spouse, Martina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martina
Context triple: [Heraclius, spouse, Martina]
  • A. Renata
    Renata is a young Venetian woman who becomes the poignant love interest of an aging American colonel in Ernest Hemingway’s novel "Across the River and Into the Trees."
  • B. Marta
    Marta is a feminine given name commonly used in many European and Latin American countries, often considered a variant of the name Martha.
  • C. Marta
    Marta is a legendary Brazilian footballer widely regarded as one of the greatest women’s players of all time.
  • D. Marta
    Marta is a small Italian town in the Lazio region, situated on the southern shore of Lake Bolsena and known for its lakeside scenery and historic center.
  • E. Martina Martini
    Martina Martini is an individual notable for sharing the surname associated with the famous Martini brand or family name.
  • 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: Martina
Triple: [Heraclius, spouse, Martina]
Generated description
Martina was a Byzantine empress and the second wife of Emperor Heraclius, known for her controversial influence at court and her role in the empire’s turbulent 7th-century politics.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martina
Target entity description: Martina was a Byzantine empress and the second wife of Emperor Heraclius, known for her controversial influence at court and her role in the empire’s turbulent 7th-century politics.
  • A. Renata
    Renata is a young Venetian woman who becomes the poignant love interest of an aging American colonel in Ernest Hemingway’s novel "Across the River and Into the Trees."
  • B. Marta
    Marta is a feminine given name commonly used in many European and Latin American countries, often considered a variant of the name Martha.
  • C. Marta
    Marta is a legendary Brazilian footballer widely regarded as one of the greatest women’s players of all time.
  • D. Marta
    Marta is a small Italian town in the Lazio region, situated on the southern shore of Lake Bolsena and known for its lakeside scenery and historic center.
  • E. Martina Martini
    Martina Martini is an individual notable for sharing the surname associated with the famous Martini brand or family name.
  • 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_69ad85de1b988190a45f8dbfebc806fc completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc35acf2c81908f60168e93b773b1 completed March 8, 2026, 6:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b44f2e464881909d62dd2fad811a83 completed March 13, 2026, 5:53 p.m.
NEDg Description generation batch_69b45092464c8190b9ad6db8c8845026 completed March 13, 2026, 5:59 p.m.
NED2 Entity disambiguation (via description) batch_69b450f261548190b5cd667b35453dcb completed March 13, 2026, 6:01 p.m.
Created at: March 8, 2026, 3:24 p.m.