Triple
T38273943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haiti |
E1021290
|
entity |
| Predicate | nearestMaritimeNeighbor |
P758
|
FINISHED |
| Object | Cuba |
—
|
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: Cuba | Statement: [Haiti, nearestMaritimeNeighbor, Cuba]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearestMaritimeNeighbor Context triple: [Haiti, nearestMaritimeNeighbor, Cuba]
-
A.
nearestCityAcrossWater
Indicates that one city is the closest city to another city when considering only routes or separation across a body of water.
-
B.
nearestSea
Indicates that one location is the closest sea to a given place compared to all other seas.
-
C.
nearestCoastalCity
Indicates that one city is the closest coastal city to another location or city, based on geographic distance.
-
D.
nearestMainlandPoint
Indicates the relationship where a location is associated with the closest point on the mainland to that location.
-
E.
neighboringCountryBySea
chosen
Indicates that one country is adjacent to another with their territories touching via a shared sea boundary rather than solely by land.
- 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_69fcd867f36081908c88c55a6a1404c1 |
completed | May 7, 2026, 6:22 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f47b188190b4cf4b4c748d9d03 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:30 p.m.