Triple

T10453472
Position Surface form Disambiguated ID Type / Status
Subject The Last Legion E246490 entity
Predicate mainCharacter P1183 FINISHED
Object Ambrosinus
Ambrosinus is a central character in the historical fantasy film "The Last Legion," portrayed as a wise and enigmatic mentor with deep knowledge of ancient lore and prophecy.
E863502 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: Ambrosinus | Statement: [The Last Legion, mainCharacter, Ambrosinus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambrosinus
Context triple: [The Last Legion, mainCharacter, Ambrosinus]
  • A. Ambrosius Flume
    Ambrosius Flume is a wizarding confectioner in the Harry Potter universe, best known as the proprietor of the popular sweet shop Honeydukes in Hogsmeade.
  • B. Martinus
    Martinus is the given first name of Dutch sprinter and later police officer Tinus Osendarp, a notable athlete of the 1930s.
  • C. Aretus
    Aretus is a minor figure in Greek mythology known primarily as one of the sons of the wise Pylian king Nestor.
  • D. Ager Pomptinus
    Ager Pomptinus was a marshy lowland region in ancient Latium, southeast of Rome, known for its later Roman drainage and agricultural development.
  • E. Coreius
    Coreius is a genus of freshwater cypriniform fishes native to East Asia, commonly found in large rivers such as the Yangtze.
  • 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: Ambrosinus
Triple: [The Last Legion, mainCharacter, Ambrosinus]
Generated description
Ambrosinus is a central character in the historical fantasy film "The Last Legion," portrayed as a wise and enigmatic mentor with deep knowledge of ancient lore and prophecy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ambrosinus
Target entity description: Ambrosinus is a central character in the historical fantasy film "The Last Legion," portrayed as a wise and enigmatic mentor with deep knowledge of ancient lore and prophecy.
  • A. Ambrosius Flume
    Ambrosius Flume is a wizarding confectioner in the Harry Potter universe, best known as the proprietor of the popular sweet shop Honeydukes in Hogsmeade.
  • B. Martinus
    Martinus is the given first name of Dutch sprinter and later police officer Tinus Osendarp, a notable athlete of the 1930s.
  • C. Aretus
    Aretus is a minor figure in Greek mythology known primarily as one of the sons of the wise Pylian king Nestor.
  • D. Ager Pomptinus
    Ager Pomptinus was a marshy lowland region in ancient Latium, southeast of Rome, known for its later Roman drainage and agricultural development.
  • E. Coreius
    Coreius is a genus of freshwater cypriniform fishes native to East Asia, commonly found in large rivers such as the Yangtze.
  • 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_69d381c04fe08190957c26c526a3b05a completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4fe0d73d48190acb687b96918e0cf completed April 7, 2026, 12:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69d87f07c9f48190b0fce7740a2e003a completed April 10, 2026, 4:39 a.m.
NEDg Description generation batch_69d886c562c081908aae846da8efb1a5 completed April 10, 2026, 5:12 a.m.
NED2 Entity disambiguation (via description) batch_69d88dce21448190b093b4f548e29f84 completed April 10, 2026, 5:42 a.m.
Created at: April 6, 2026, 12:17 p.m.