Triple

T13761455
Position Surface form Disambiguated ID Type / Status
Subject Julian clan E330618 entity
Predicate hasCognomen P6662 FINISHED
Object Caesar
Caesar was the famous cognomen of the Roman statesman and general Gaius Julius Caesar, whose name later became synonymous with imperial rule.
E813912 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: Caesar | Statement: [Julian clan, hasCognomen, Caesar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caesar
Context triple: [Julian clan, hasCognomen, Caesar]
  • A. Caesar
    Caesar was the title given to junior co-emperors in the Roman Empire, particularly formalized as the subordinate rank within Diocletian’s Tetrarchic system.
  • B. Caesar
    Caesar is a fictional character portrayed by Karl Urban, likely known from his roles in film or television.
  • C. Caesar
    Caesar is the intelligent, evolved chimpanzee who leads the apes in the modern Planet of the Apes film series.
  • D. Caesar
    Caesar is one of the two canine protagonists in Robert Burns’s poem “The Twa Dogs,” serving as the more privileged dog whose conversations explore social class and human nature.
  • E. Caesar
    Caesar is a key character in Colson Whitehead’s novel "The Underground Railroad," an enslaved man whose partnership with Cora drives their perilous escape from bondage.
  • 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: Caesar
Triple: [Julian clan, hasCognomen, Caesar]
Generated description
Caesar was the famous cognomen of the Roman statesman and general Gaius Julius Caesar, whose name later became synonymous with imperial rule.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Caesar
Target entity description: Caesar was the famous cognomen of the Roman statesman and general Gaius Julius Caesar, whose name later became synonymous with imperial rule.
  • A. Caesar chosen
    Caesar is a prominent Classical Latin author best known for his commentaries on the Gallic and Civil Wars, which are key sources for both Latin prose style and Roman history.
  • B. Caesar
    Caesar was the title given to junior co-emperors in the Roman Empire, particularly formalized as the subordinate rank within Diocletian’s Tetrarchic system.
  • C. Caesar
    Caesar is a central character in Shakespeare’s play "Julius Caesar," depicted as a powerful Roman leader whose assassination triggers political chaos and moral conflict.
  • D. Caesar
    Caesar is the intelligent, evolved chimpanzee who leads the apes in the modern Planet of the Apes film series.
  • E. Caesar
    Caesar is a fictional character portrayed by Karl Urban, likely known from his roles in film or television.
  • F. None of above.

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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02250f4881908d5193b3d5d25844 completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a8606dbc8190b0f7c38583986141 completed May 3, 2026, 7:56 p.m.
NEDg Description generation batch_69f7ac4f847c8190ab8be535e5399c79 completed May 3, 2026, 8:13 p.m.
NED2 Entity disambiguation (via description) batch_69f7acdf70f8819092700c7b6b619d13 completed May 3, 2026, 8:15 p.m.
Created at: April 9, 2026, 10:09 p.m.