Triple

T4394340
Position Surface form Disambiguated ID Type / Status
Subject Martha Vickers E99447 entity
Predicate spouse P13 FINISHED
Object Manuel Rojas
Manuel Rojas was the husband of American film actress and model Martha Vickers.
 E444851 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: Manuel Rojas | Statement: [Martha Vickers, spouse, Manuel Rojas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Manuel Rojas
Context triple: [Martha Vickers, spouse, Manuel Rojas]
  • A. Juan Escalona
    Juan Escalona was a political and military figure who played a significant leadership role during the brief existence of the First Republic of Venezuela in the early 19th century.
  • B. Pedro Rollán
    Pedro Rollán is a Spanish politician who serves as the president of the Senate of Spain.
  • C. Martín Zorreguieta
    Martín Zorreguieta is an Argentine businessman and restaurateur best known as the younger brother of Queen Máxima of the Netherlands.
  • D. Silvino Lobos
    Silvino Lobos is a rural municipality in the province of Northern Samar in the Philippines, known for its mountainous terrain and largely agricultural economy.
  • E. Jorge Zorreguieta
    Jorge Zorreguieta was an Argentine agricultural official and politician best known internationally as the father of Queen Máxima of the Netherlands and for his controversial role in Argentina’s military dictatorship.
  • 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: Manuel Rojas
Triple: [Martha Vickers, spouse, Manuel Rojas]
Generated description
Manuel Rojas was the husband of American film actress and model Martha Vickers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Manuel Rojas
Target entity description: Manuel Rojas was the husband of American film actress and model Martha Vickers.
  • A. Juan Escalona
    Juan Escalona was a political and military figure who played a significant leadership role during the brief existence of the First Republic of Venezuela in the early 19th century.
  • B. Pedro Rollán
    Pedro Rollán is a Spanish politician who serves as the president of the Senate of Spain.
  • C. Martín Zorreguieta
    Martín Zorreguieta is an Argentine businessman and restaurateur best known as the younger brother of Queen Máxima of the Netherlands.
  • D. Silvino Lobos
    Silvino Lobos is a rural municipality in the province of Northern Samar in the Philippines, known for its mountainous terrain and largely agricultural economy.
  • E. Jorge Zorreguieta
    Jorge Zorreguieta was an Argentine agricultural official and politician best known internationally as the father of Queen Máxima of the Netherlands and for his controversial role in Argentina’s military dictatorship.
  • 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_69b345506b408190b0e3dee616738a7d completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352a9c8b88190a7894a40be4996f0 completed March 12, 2026, 11:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b66b2e5cec81909768673ab3f341d5 completed March 15, 2026, 8:17 a.m.
NEDg Description generation batch_69b66b91ca408190a7d3443c8b4b8d61 completed March 15, 2026, 8:19 a.m.
NED2 Entity disambiguation (via description) batch_69b66c9693088190bd3f8c4b82934e10 completed March 15, 2026, 8:23 a.m.
Created at: March 12, 2026, 11:20 p.m.