Triple

T17119141
Position Surface form Disambiguated ID Type / Status
Subject President of the Legislative Council of Bermuda E415417 entity
Predicate styleOfAddress P536 FINISHED
Object Madam President
Madam President is the formal style of address used for a woman serving as President of the Legislative Council of Bermuda.
E985879 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: Madam President | Statement: [President of the Legislative Council of Bermuda, styleOfAddress, Madam President]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Madam President
Context triple: [President of the Legislative Council of Bermuda, styleOfAddress, Madam President]
  • A. Madam President
    Madam President is the formal style of address used for a woman serving as President of the Senate of the Parliament of the Czech Republic.
  • B. Madam President
    "Madam President" is the formal style of address used for a female President of the United States.
  • C. Madam President
    Madam President is the formal style of address used for a woman serving as President of the Senate in Belgium.
  • D. Madam President
    Madam President is the formal style of address used for a female head of state serving as President of Romania.
  • E. Madam President
    Madam President is an honorific title used for a female head of state or government, notably associated with Indonesia’s former president Megawati Sukarnoputri.
  • 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: Madam President
Triple: [President of the Legislative Council of Bermuda, styleOfAddress, Madam President]
Generated description
Madam President is the formal style of address used for a woman serving as President of the Legislative Council of Bermuda.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Madam President
Target entity description: Madam President is the formal style of address used for a woman serving as President of the Legislative Council of Bermuda.
  • A. Madam President chosen
    Madam President is the formal style of address used for a woman serving as the presiding officer of a legislative council or similar parliamentary body.
  • B. Madam President
    Madam President is the formal style of address used for a woman serving as President of the Senate in Belgium.
  • C. Madam President
    "Madam President" is the formal style of address used for a female President of the United States.
  • D. Madam President
    "Madam President" is the formal style of address used for a woman serving as President of the Swiss Confederation.
  • E. Madam President
    Madam President is the formal style of address used for a female head of state serving as President of Romania.
  • 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_69d886d090cc8190a39cb94992586905 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3e8086a388190a655a044feccab14 completed April 18, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a013a0e11108190bfcf858142aa9ff3 completed May 11, 2026, 2:08 a.m.
NEDg Description generation batch_6a013b749680819097159f0fdc379f2c completed May 11, 2026, 2:14 a.m.
NED2 Entity disambiguation (via description) batch_6a013bf9ef508190aac1155680f33eaf completed May 11, 2026, 2:16 a.m.
Created at: April 10, 2026, 5:35 a.m.