Triple

T8897521
Position Surface form Disambiguated ID Type / Status
Subject Sir Kay E211842 entity
Predicate nameInLatin P3646 FINISHED
Object Caius
Caius is the Latinized name of Sir Kay, the legendary knight of King Arthur’s court in Arthurian mythology.
 E803697 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: Caius | Statement: [Sir Kay, nameInLatin, Caius]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Caius
Context triple: [Sir Kay, nameInLatin, Caius]
  • A. Caius
    Caius is one of the three ancient vampire rulers of the Volturi coven in the Twilight series, known for his cruelty and strict enforcement of vampire law.
  • B. Gaius
    Gaius is an early Christian believer and church member addressed personally and commended by the Apostle John in the New Testament.
  • C. Gaius
    Gaius was a prominent 2nd-century Roman jurist whose legal writings, especially his Institutes, significantly shaped later Roman and European legal traditions.
  • D. Gaius
    Gaius is the praenomen (personal name) of the Roman lawyer, author, and magistrate known as Pliny the Younger.
  • E. Gaius
    Gaius is a common Roman praenomen (given name) frequently borne by notable figures of the Roman Republic and Empire.
  • 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: Caius
Triple: [Sir Kay, nameInLatin, Caius]
Generated description
Caius is the Latinized name of Sir Kay, the legendary knight of King Arthur’s court in Arthurian mythology.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Caius
Target entity description: Caius is the Latinized name of Sir Kay, the legendary knight of King Arthur’s court in Arthurian mythology.
  • A. Caius
    Caius is one of the three ancient vampire rulers of the Volturi coven in the Twilight series, known for his cruelty and strict enforcement of vampire law.
  • B. Gaius
    Gaius is an early Christian believer and church member addressed personally and commended by the Apostle John in the New Testament.
  • C. Gaius
    Gaius was a prominent 2nd-century Roman jurist whose legal writings, especially his Institutes, significantly shaped later Roman and European legal traditions.
  • D. Gaius
    Gaius is the praenomen (personal name) of the Roman lawyer, author, and magistrate known as Pliny the Younger.
  • E. Gaius
    Gaius is a common Roman praenomen (given name) frequently borne by notable figures of the Roman Republic and Empire.
  • 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_69ca83918d3081909b326fa3750cb8c8 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6424a8c08190aef2aa2079dd85f1 completed April 1, 2026, 12:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69d139a069f881909cc59bad0f110830 completed April 4, 2026, 4:17 p.m.
NEDg Description generation batch_69d13bb4e3688190aaf6a0ba117296ae completed April 4, 2026, 4:26 p.m.
NED2 Entity disambiguation (via description) batch_69d13c1b8fd481909dc4a98d64301d2f completed April 4, 2026, 4:28 p.m.
Created at: March 30, 2026, 6:54 p.m.