Triple
T38273939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haiti |
E1021290
|
entity |
| Predicate | maritimeVicinity |
P117087
|
FINISHED |
| Object | Greater Antilles |
—
|
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: Greater Antilles | Statement: [Haiti, maritimeVicinity, Greater Antilles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: maritimeVicinity Context triple: [Haiti, maritimeVicinity, Greater Antilles]
-
A.
marineArea
Indicates a relationship where an entity is located in, associated with, or relevant to a specific marine or oceanic area.
-
B.
hasNearbyMarineFeature
chosen
Indicates that one entity is located close to a marine geographic feature associated with the other entity.
-
C.
maritimeDomain
Indicates a relationship or activity that occurs within, affects, or is specifically associated with the maritime domain (seas, oceans, and related maritime operations).
-
D.
nearestSea
Indicates that one location is the closest sea to a given place compared to all other seas.
-
E.
marineAreaShare
Indicates the proportion of a larger marine area that is occupied, controlled, or otherwise attributed to a specific entity.
- 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_69f76dee198c8190bf5109421e47a658 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:30 p.m.