Triple
T18019759
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OMR |
E431085
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Saint-Martin |
—
|
NE NERFINISHED |
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: Saint-Martin | Statement: [OMR, hasMember, Saint-Martin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saint-Martin Context triple: [OMR, hasMember, Saint-Martin]
-
A.
de Saint-Martin
de Saint-Martin is the surname of Louis Claude de Saint-Martin, an 18th-century French philosopher and mystic associated with Christian theosophy and esoteric thought.
-
B.
Saint Martin
chosen
Saint Martin is a Caribbean island divided between French and Dutch sovereignty, known for its tourism, beaches, and blend of European and Caribbean cultures.
-
C.
Saint Martin
Saint Martin is a revered Christian saint, most commonly associated with Martin of Tours, known for his humility, charity, and role as a 4th-century bishop in Gaul.
-
D.
St. Martin
St. Martin is a coastal community in Mississippi known for its proximity to Biloxi Bay and the Gulf Coast region.
-
E.
Martinique
Martinique is a Caribbean island and French overseas region known for its blend of French and Creole culture, volcanic landscapes, and beaches.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b9c09fdc819097a7fa07d44b0505 |
completed | April 19, 2026, 11:17 a.m. |
Created at: April 10, 2026, 10:24 a.m.