Triple
T6901777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Northern Haiti |
E159511
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Dondon
Dondon is a historic commune in northern Haiti known for its colonial-era architecture, coffee production, and nearby cave systems with pre-Columbian rock art.
|
E627221
|
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: Dondon | Statement: [Northern Haiti, contains, Dondon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dondon Context triple: [Northern Haiti, contains, Dondon]
-
A.
Pogi
Pogi is a locality or frazione within the municipality of Bucine in the Tuscany region of Italy.
-
B.
Plaridel
Plaridel is a municipality in the province of Bulacan in the Philippines, known for its historical significance and proximity to Metro Manila.
-
C.
Tayabas
Tayabas is a historic city in the province of Quezon in the Calabarzon region of the Philippines, known for its Spanish-era heritage structures and cultural festivals.
-
D.
Sta. Cruz
Sta. Cruz is a coastal municipality in the province of Zambales in the Philippines, known for its fishing communities and proximity to the West Philippine Sea.
-
E.
Legazpi
Legazpi is a Madrid Metro station and transport hub located in the Arganzuela district of Madrid, Spain.
- 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: Dondon Triple: [Northern Haiti, contains, Dondon]
Generated description
Dondon is a historic commune in northern Haiti known for its colonial-era architecture, coffee production, and nearby cave systems with pre-Columbian rock art.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dondon Target entity description: Dondon is a historic commune in northern Haiti known for its colonial-era architecture, coffee production, and nearby cave systems with pre-Columbian rock art.
-
A.
Pogi
Pogi is a locality or frazione within the municipality of Bucine in the Tuscany region of Italy.
-
B.
Plaridel
Plaridel is a municipality in the province of Bulacan in the Philippines, known for its historical significance and proximity to Metro Manila.
-
C.
Tayabas
Tayabas is a historic city in the province of Quezon in the Calabarzon region of the Philippines, known for its Spanish-era heritage structures and cultural festivals.
-
D.
Sta. Cruz
Sta. Cruz is a coastal municipality in the province of Zambales in the Philippines, known for its fishing communities and proximity to the West Philippine Sea.
-
E.
Legazpi
Legazpi is a Madrid Metro station and transport hub located in the Arganzuela district of Madrid, Spain.
- 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_69c6883822e0819091e321526f20ae0a |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d98749208190842ac075255ca249 |
completed | March 27, 2026, 7:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c748f0dc448190914e38d780644698 |
completed | March 28, 2026, 3:20 a.m. |
| NEDg | Description generation | batch_69c749f7ab5c8190ab823fac27f7484d |
completed | March 28, 2026, 3:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c74a6f828c8190bf0cc56227b1a5b2 |
completed | March 28, 2026, 3:26 a.m. |
Created at: March 27, 2026, 2:24 p.m.