Triple

T3693510
Position Surface form Disambiguated ID Type / Status
Subject President of Dominica E78398 entity
Predicate officeHoldersInclude P537 FINISHED
Object Crispin Sorhaindo
Crispin Sorhaindo was a Dominican politician who served as President of the Commonwealth of Dominica in the 1990s.
E379636 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: Crispin Sorhaindo | Statement: [President of Dominica, officeHoldersInclude, Crispin Sorhaindo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Crispin Sorhaindo
Context triple: [President of Dominica, officeHoldersInclude, Crispin Sorhaindo]
  • A. Ethan Maniquis
    Ethan Maniquis is a film editor and director best known for co-directing the action exploitation film "Machete."
  • B. Julian de Guzman
    Julian de Guzman is a retired Canadian midfielder who became one of the national team’s most influential players and the first Canadian to play in Spain’s La Liga.
  • C. David Luan
    David Luan is an AI researcher and entrepreneur known for his work on large language models at OpenAI and as co-founder and CEO of Adept AI.
  • D. Colin Emmanuel
    Colin Emmanuel is a British music producer and songwriter known for his work in UK R&B and hip hop.
  • E. Josiah Ng
    Josiah Ng is a Malaysian track cyclist best known as a multiple Olympian and Commonwealth Games medalist in the keirin event.
  • 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: Crispin Sorhaindo
Triple: [President of Dominica, officeHoldersInclude, Crispin Sorhaindo]
Generated description
Crispin Sorhaindo was a Dominican politician who served as President of the Commonwealth of Dominica in the 1990s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Crispin Sorhaindo
Target entity description: Crispin Sorhaindo was a Dominican politician who served as President of the Commonwealth of Dominica in the 1990s.
  • A. Ethan Maniquis
    Ethan Maniquis is a film editor and director best known for co-directing the action exploitation film "Machete."
  • B. Julian de Guzman
    Julian de Guzman is a retired Canadian midfielder who became one of the national team’s most influential players and the first Canadian to play in Spain’s La Liga.
  • C. David Luan
    David Luan is an AI researcher and entrepreneur known for his work on large language models at OpenAI and as co-founder and CEO of Adept AI.
  • D. Colin Emmanuel
    Colin Emmanuel is a British music producer and songwriter known for his work in UK R&B and hip hop.
  • E. Josiah Ng
    Josiah Ng is a Malaysian track cyclist best known as a multiple Olympian and Commonwealth Games medalist in the keirin event.
  • 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_69ad85e3b1888190abc983e06968696d completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc4e9e4748190aa178692ef27e3a6 completed March 8, 2026, 6:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4c3d0f2d88190b31e8c336f1a1bf3 completed March 14, 2026, 2:11 a.m.
NEDg Description generation batch_69b4c5280d788190b59b23acf5f77811 completed March 14, 2026, 2:17 a.m.
NED2 Entity disambiguation (via description) batch_69b4c58b13c48190b975e61000aa1f05 completed March 14, 2026, 2:18 a.m.
Created at: March 8, 2026, 3:26 p.m.