Triple

T21341083
Position Surface form Disambiguated ID Type / Status
Subject Philip of Savoy E526192 entity
Predicate givenName P17 FINISHED
Object Philip
Philip of Savoy was a 13th-century nobleman who briefly ruled as Count of Savoy and played a significant role in the politics of medieval Europe.
E1478964 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: Philip | Statement: [Philip of Savoy, givenName, Philip]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Philip
Context triple: [Philip of Savoy, givenName, Philip]
  • A. Philip
    Philip is the given first name of American comedian and actor Phil Silvers, famed for his role as Sgt. Bilko.
  • B. Philip
    Philip is the given first name of Phil Lynott, the charismatic Irish musician best known as the frontman and bassist of the rock band Thin Lizzy.
  • C. Philip
    Philip is the given name of Philip Yorke, 1st Earl of Hardwicke, an influential 18th-century British lawyer and Lord Chancellor.
  • D. Philip
    Philip was the given name of Philip III of France, a 13th-century Capetian king who ruled from 1270 to 1285.
  • E. Philip
    Philip is the given name of Prince Carl Philip, Duke of Värmland, a member of the Swedish royal family.
  • 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: Philip
Triple: [Philip of Savoy, givenName, Philip]
Generated description
Philip of Savoy was a 13th-century nobleman who briefly ruled as Count of Savoy and played a significant role in the politics of medieval Europe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Philip
Target entity description: Philip of Savoy was a 13th-century nobleman who briefly ruled as Count of Savoy and played a significant role in the politics of medieval Europe.
  • A. Philip
    Philip was a medieval nobleman who held the title of Prince of Taranto and played a significant role in the politics of the Latin states in Greece and southern Italy.
  • B. Philip
    Philip was the given name of Philip IV of France, the medieval Capetian king known for his conflicts with the papacy and the suppression of the Knights Templar.
  • C. Philip
    Philip was the given name of Philip V of France, a Capetian king who ruled France and Navarre in the early 14th century.
  • D. Philip
    Philip was a common medieval European given name borne by several notable rulers, including kings of France and other realms.
  • E. Philip
    Philip was the given name of Philip III of France, a 13th-century Capetian king who ruled from 1270 to 1285.
  • 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_69e0b51c33048190ab27cede74ef798c completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69ee5ba7ce3c8190ba5ded980a9866f2 completed April 26, 2026, 6:38 p.m.
NED1 Entity disambiguation (via context triple) batch_6a09a5c260dc8190be7acb83b1c9c832 completed May 17, 2026, 11:25 a.m.
NEDg Description generation batch_6a09a8aef61c8190985aad0637b8fadd completed May 17, 2026, 11:38 a.m.
NED2 Entity disambiguation (via description) batch_6a09a915a57c81909b5b1bb7042957a0 completed May 17, 2026, 11:40 a.m.
Created at: April 16, 2026, 4:44 p.m.