Triple

T16550497
Position Surface form Disambiguated ID Type / Status
Subject Capesterre-de-Marie-Galante E402058 entity
Predicate demonym P191 FINISHED
Object Capesterrien
A Capesterrien is a resident or native of Capesterre-de-Marie-Galante, a commune on the island of Marie-Galante in Guadeloupe.
 E1219445 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: Capesterrien | Statement: [Capesterre-de-Marie-Galante, demonym, Capesterrien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Capesterrien
Context triple: [Capesterre-de-Marie-Galante, demonym, Capesterrien]
  • A. Morisyen
    Morisyen is the French-based Creole language widely spoken in Mauritius and used as a key marker of the island’s national identity.
  • B. Brabantic
    Brabantic is a group of closely related Dutch dialects traditionally spoken in the historical Duchy of Brabant, spanning parts of the Netherlands and Belgium.
  • C. Rennellese
    Rennellese are the indigenous Polynesian people native to Rennell and Bellona Islands in the Solomon Islands, known for their distinct language and cultural traditions.
  • D. Jèrriais
    Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
  • E. Saybrugian
    The Saybrugian is the official mascot and symbolic figure representing Saybrook College at Yale University.
  • 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: Capesterrien
Triple: [Capesterre-de-Marie-Galante, demonym, Capesterrien]
Generated description
A Capesterrien is a resident or native of Capesterre-de-Marie-Galante, a commune on the island of Marie-Galante in Guadeloupe.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Capesterrien
Target entity description: A Capesterrien is a resident or native of Capesterre-de-Marie-Galante, a commune on the island of Marie-Galante in Guadeloupe.
  • A. Morisyen
    Morisyen is the French-based Creole language widely spoken in Mauritius and used as a key marker of the island’s national identity.
  • B. Brabantic
    Brabantic is a group of closely related Dutch dialects traditionally spoken in the historical Duchy of Brabant, spanning parts of the Netherlands and Belgium.
  • C. Rennellese
    Rennellese are the indigenous Polynesian people native to Rennell and Bellona Islands in the Solomon Islands, known for their distinct language and cultural traditions.
  • D. Jèrriais
    Jèrriais is a Norman Romance language traditionally spoken on the island of Jersey in the Channel Islands.
  • E. Saybrugian
    The Saybrugian is the official mascot and symbolic figure representing Saybrook College at Yale University.
  • 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34fc451dc8190b571d5010f4017f4 completed April 18, 2026, 9:32 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0067b6ca44819085145eb48356e7b4 completed May 10, 2026, 11:10 a.m.
NEDg Description generation batch_6a00687d228081909d0a39f2c23d4e4d completed May 10, 2026, 11:14 a.m.
NED2 Entity disambiguation (via description) batch_6a006907419881909e8f71714bbe054a completed May 10, 2026, 11:16 a.m.
Created at: April 10, 2026, 5:15 a.m.