Triple
T12168565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Petro lwa |
E289895
|
entity |
| Predicate | includes |
P1393
|
FINISHED |
| Object |
Marinette
Marinette is a fearsome and fiery Petro lwa in Haitian Vodou, often associated with aggression, protection, and transformative power.
|
E964375
|
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: Marinette | Statement: [Petro lwa, includes, Marinette]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marinette Context triple: [Petro lwa, includes, Marinette]
-
A.
Camille Roux
Camille Roux was an artist associated with the Impressionist movement who participated in the historic Impressionist exhibitions in late 19th-century France.
-
B.
Marthette
Marthette is a feminine given name, used as a diminutive or affectionate variant of the name Marthe.
-
C.
Mariette Lydis
Mariette Lydis was an Austrian-Argentine painter and illustrator known for her expressive, often melancholic depictions of women and marginalized figures in early 20th-century art.
-
D.
Adrienne Lubeau
Adrienne Lubeau is known as the former wife of influential American street photographer Garry Winogrand.
-
E.
Azélie
Azélie is a short story by Kate Chopin, included in her 1897 collection *A Night in Acadie*, that explores themes of love, culture, and identity in a Louisiana setting.
- 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: Marinette Triple: [Petro lwa, includes, Marinette]
Generated description
Marinette is a fearsome and fiery Petro lwa in Haitian Vodou, often associated with aggression, protection, and transformative power.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marinette Target entity description: Marinette is a fearsome and fiery Petro lwa in Haitian Vodou, often associated with aggression, protection, and transformative power.
-
A.
Camille Roux
Camille Roux was an artist associated with the Impressionist movement who participated in the historic Impressionist exhibitions in late 19th-century France.
-
B.
Marthette
Marthette is a feminine given name, used as a diminutive or affectionate variant of the name Marthe.
-
C.
Mariette Lydis
Mariette Lydis was an Austrian-Argentine painter and illustrator known for her expressive, often melancholic depictions of women and marginalized figures in early 20th-century art.
-
D.
Adrienne Lubeau
Adrienne Lubeau is known as the former wife of influential American street photographer Garry Winogrand.
-
E.
Azélie
Azélie is a short story by Kate Chopin, included in her 1897 collection *A Night in Acadie*, that explores themes of love, culture, and identity in a Louisiana setting.
- 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_69d6ab4d6c00819095a9a7c35de83cfb |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d915d85c088190a74fb7590877659b |
completed | April 10, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f5f6a45568819090662cd3547c9253 |
completed | May 2, 2026, 1:05 p.m. |
| NEDg | Description generation | batch_69f5ff826ea08190a6780351e4b927ac |
completed | May 2, 2026, 1:43 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f60185ce8c8190abe3b1f633aac55d |
completed | May 2, 2026, 1:52 p.m. |
Created at: April 8, 2026, 9:50 p.m.