Triple
T35836463
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Overseas Railroad |
E1035952
|
entity |
| Predicate | crossedBodyOfWater |
P15424
|
FINISHED |
| Object | Straits of Florida |
—
|
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: Straits of Florida | Statement: [Overseas Railroad, crossedBodyOfWater, Straits of Florida]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crossedBodyOfWater Context triple: [Overseas Railroad, crossedBodyOfWater, Straits of Florida]
-
A.
crossesWaterBody
chosen
Indicates that an entity moves from one side of a water body to the other by passing over, through, or across it.
-
B.
waterwayTypeCrossed
Indicates the specific kind of waterway (e.g., river, canal, stream) that is being crossed in the described relationship or action.
-
C.
crossingRegime
Indicates the regulatory or procedural framework under which a boundary or checkpoint is crossed.
-
D.
bodyOfWaterOnOtherSide
Indicates that one entity is located across a body of water from the other entity, with the water lying between them.
-
E.
acrossWaterFrom
Indicates that two entities are located on opposite sides of a body of water, separated by that water.
- 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_69f76e192a94819082db360cb91e6a8d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:06 p.m.