Triple
T29197297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Outer Harbour |
E740161
|
entity |
| Predicate | navigationHazardPotential |
P17706
|
FINISHED |
| Object | higher due to exposure and traffic of large vessels |
—
|
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: higher due to exposure and traffic of large vessels | Statement: [Outer Harbour, navigationHazardPotential, higher due to exposure and traffic of large vessels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: navigationHazardPotential Context triple: [Outer Harbour, navigationHazardPotential, higher due to exposure and traffic of large vessels]
-
A.
hasNavigationHazard
Indicates that something presents or contains a condition, object, or feature that poses a risk or obstacle to safe navigation.
-
B.
hasNavigationHazardRelevance
chosen
Indicates that something is relevant to, affected by, or poses a potential hazard to navigation.
-
C.
hasObjectiveHazards
Indicates that an entity is associated with concrete, externally verifiable dangers or risks.
-
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.
locatedNearHazard
Indicates that one entity is situated in close physical proximity to a hazardous object, area, or condition.
- 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_69f07cb8033c8190b8807e219a14333d |
completed | April 28, 2026, 9:24 a.m. |
| NER | Named-entity recognition | batch_69f663c2f7a481908481c41c06579b39 |
completed | May 2, 2026, 8:51 p.m. |
| PD | Predicate disambiguation | batch_69f65c24f8b48190af81b575f3c15be5 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 12:04 p.m.