Triple

T7738408
Position Surface form Disambiguated ID Type / Status
Subject Jacmel E175441 entity
Predicate nativeName P15 FINISHED
Object Jakmèl
Jakmèl is the Haitian Creole name for Jacmel, a historic coastal city in southern Haiti known for its vibrant arts scene, colonial architecture, and annual Carnival celebrations.
E685330 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: Jakmèl | Statement: [Jacmel, nativeName, Jakmèl]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jakmèl
Context triple: [Jacmel, nativeName, Jakmèl]
  • A. Jakusko
    Jakusko is a local government area in northeastern Nigeria known for its rural communities and location within Yobe State.
  • B. Krempna
    Krempna is a small village in southeastern Poland that serves as a gateway and service center for visitors to Magura National Park in the Low Beskid Mountains.
  • C. Zihl
    Zihl is a river in Switzerland that serves as a key tributary within the Aare river system.
  • D. Kremmen
    Kremmen is a small town and municipality in the Oberhavel district of the German state of Brandenburg.
  • E. Giogha
    Giogha is the Scottish Gaelic name for the small Hebridean island of Gigha off the west coast of Kintyre in Scotland.
  • 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: Jakmèl
Triple: [Jacmel, nativeName, Jakmèl]
Generated description
Jakmèl is the Haitian Creole name for Jacmel, a historic coastal city in southern Haiti known for its vibrant arts scene, colonial architecture, and annual Carnival celebrations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jakmèl
Target entity description: Jakmèl is the Haitian Creole name for Jacmel, a historic coastal city in southern Haiti known for its vibrant arts scene, colonial architecture, and annual Carnival celebrations.
  • A. Jakusko
    Jakusko is a local government area in northeastern Nigeria known for its rural communities and location within Yobe State.
  • B. Krempna
    Krempna is a small village in southeastern Poland that serves as a gateway and service center for visitors to Magura National Park in the Low Beskid Mountains.
  • C. Zihl
    Zihl is a river in Switzerland that serves as a key tributary within the Aare river system.
  • D. Kremmen
    Kremmen is a small town and municipality in the Oberhavel district of the German state of Brandenburg.
  • E. Giogha
    Giogha is the Scottish Gaelic name for the small Hebridean island of Gigha off the west coast of Kintyre in Scotland.
  • 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_69c6995f9c60819092e386192bd63c6f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c7035bcd94819080d5553e602e6c61 completed March 27, 2026, 10:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be3db6a481909750c13f9141b84b completed March 29, 2026, 5:53 a.m.
NEDg Description generation batch_69c8becfaf80819095b8415b4b9f66d0 completed March 29, 2026, 5:55 a.m.
NED2 Entity disambiguation (via description) batch_69c8bf3200f8819083f0a38cb03491a8 completed March 29, 2026, 5:57 a.m.
Created at: March 27, 2026, 4:07 p.m.