Triple
T12168931
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saut-d’Eau pilgrimage |
E289903
|
entity |
| Predicate | honors |
P2354
|
FINISHED |
| Object | Erzulie Dantor |
E970230
|
NE FINISHED |
How this triple was built (2 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: Erzulie Dantor | Statement: [Saut-d’Eau pilgrimage, honors, Erzulie Dantor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Erzulie Dantor Context triple: [Saut-d’Eau pilgrimage, honors, Erzulie Dantor]
-
A.
Erzulie Dantor
chosen
Erzulie Dantor is a fierce, protective Haitian Vodou lwa often associated with motherhood, vengeance, and the struggles of the marginalized.
-
B.
Erzulie Freda
Erzulie Freda is a prominent Haitian Vodou spirit associated with love, beauty, luxury, and feminine sensuality.
-
C.
Moolaadé
Moolaadé is a 2004 Senegalese drama film by Ousmane Sembène that powerfully critiques female genital mutilation through the story of a village woman who offers protection to young girls seeking refuge.
-
D.
Mouloudia
Mouloudia is the popular nickname of MC Alger, one of Algeria’s most historic and successful football clubs.
-
E.
Kelaat M'Gouna
Kelaat M'Gouna is a Moroccan town famed for its rose cultivation and annual Rose Festival, attracting visitors to the Drâa-Tafilalet region.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69f61e4deb308190aa1a99a78d46b461 |
completed | May 2, 2026, 3:54 p.m. |
Created at: April 8, 2026, 9:50 p.m.