Triple
T26129343
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Overfalls Shoal lightship station |
E659192
|
entity |
| Predicate | hazardTypeMarked |
P1950
|
FINISHED |
| Object | submerged sand shoal |
—
|
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: submerged sand shoal | Statement: [Overfalls Shoal lightship station, hazardTypeMarked, submerged sand shoal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hazardTypeMarked Context triple: [Overfalls Shoal lightship station, hazardTypeMarked, submerged sand shoal]
-
A.
hazardType
chosen
Indicates the specific kind or category of hazard associated with an entity or situation.
-
B.
hasNotableHazard
Indicates that an entity is associated with a significant risk, danger, or harmful condition that is noteworthy or exceptional.
-
C.
isHazardTo
Indicates that one entity poses a potential source of danger, harm, or risk to another entity.
-
D.
hazardEncountered
Indicates that an entity has come into contact with or been exposed to a potentially dangerous or harmful condition, object, or situation.
-
E.
monitorsHazardType
Indicates that an entity observes, tracks, or keeps watch over a specified type or category of hazard.
- 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_69ee5bc2b2948190b458ad3f580af779 |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f60b9202b08190b2dca041b547d64e |
completed | May 2, 2026, 2:34 p.m. |
| PD | Predicate disambiguation | batch_69f5b0021da88190bdd4cf2698c23edf |
completed | May 2, 2026, 8:04 a.m. |
Created at: April 26, 2026, 8:13 p.m.