Triple

T3879293
Position Surface form Disambiguated ID Type / Status
Subject John, Constable of Portugal E92580 entity
Predicate givenName P17 FINISHED
Object John
John, Constable of Portugal, was a prominent 15th-century Portuguese nobleman and military leader known for his role in the consolidation of the Avis dynasty.
E394973 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: John | Statement: [John, Constable of Portugal, givenName, John]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John
Context triple: [John, Constable of Portugal, givenName, John]
  • A. John
    John H. Sununu is an American politician and engineer who served as Governor of New Hampshire and later as White House Chief of Staff under President George H. W. Bush.
  • B. John
    John is the given name of John F. Sattler, likely referring to him in a more informal or abbreviated context.
  • C. John
    John is the given name of John Peter Altgeld, a prominent 19th-century American politician and reformist governor of Illinois.
  • D. John
    John is the given name of John Ruskin, the influential 19th-century English art critic, social thinker, and writer.
  • E. John
    John Reid, Baron Reid of Cardowan, is a Scottish Labour politician who held several senior UK government posts, including Home Secretary and Defence Secretary, in the late 1990s and 2000s.
  • 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: John
Triple: [John, Constable of Portugal, givenName, John]
Generated description
John, Constable of Portugal, was a prominent 15th-century Portuguese nobleman and military leader known for his role in the consolidation of the Avis dynasty.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: John
Target entity description: John, Constable of Portugal, was a prominent 15th-century Portuguese nobleman and military leader known for his role in the consolidation of the Avis dynasty.
  • A. John
    John IV of Portugal was a 17th-century Portuguese king who restored the country's independence from Spain and founded the Braganza dynasty.
  • B. John
    John is the given name of John II of Portugal, the 15th-century king known for strengthening royal authority and advancing Portuguese exploration.
  • C. John
    John of Bohemia was a 14th-century King of Bohemia and Count of Luxembourg, renowned as a chivalric warrior who famously died fighting blind at the Battle of Crécy.
  • D. John
    John was a medieval English monarch who ruled as King John of England from 1199 to 1216 and is best known for sealing the Magna Carta.
  • E. John
    John is the given name of the English architect and dramatist John Vanbrugh, known for designing Blenheim Palace and Castle Howard.
  • 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_69aed967448c819086c4b358d37b25aa completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec7438808190b6c90fcb3000ebe9 completed March 9, 2026, 3:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51253da2081908689f06975fb4db1 completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b5132715888190bc5ba6182965e813 completed March 14, 2026, 7:49 a.m.
NED2 Entity disambiguation (via description) batch_69b513b382748190b201bc2ed068c3e6 completed March 14, 2026, 7:52 a.m.
Created at: March 9, 2026, 3:20 p.m.