Triple
T10862650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sint Maarten Day |
E256443
|
entity |
| Predicate | observedOnIsland |
P38098
|
FINISHED |
| Object | island of Saint Martin |
—
|
LITERAL 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: island of Saint Martin | Statement: [Sint Maarten Day, observedOnIsland, island of Saint Martin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observedOnIsland Context triple: [Sint Maarten Day, observedOnIsland, island of Saint Martin]
-
A.
observedOnMainIsland
chosen
Indicates that the observation or occurrence of something took place specifically on the main island, as opposed to surrounding or subsidiary islands.
-
B.
foundOnIsland
Indicates that one entity is located or discovered on an island in relation to another entity.
-
C.
seeIsland
Indicates that an entity visually perceives or observes an island.
-
D.
meetsInIsland
Indicates that two or more entities meet with each other at a location that is an island.
-
E.
onlyInhabitedIsland
Indicates that the subject is the sole inhabited island within a specified geographic or contextual set, with no other islands in that set having inhabitants.
- F. None of above.
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_69d6aa83d1448190a66d93c32394d21f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d7515238108190a72eb8cd147f223d |
completed | April 9, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69d70d308dfc81908792f98cfb871392 |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:20 p.m.