Triple
T18946557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Plymouth Breakwater Lighthouse |
E463527
|
entity |
| Predicate | originalOperation |
P58201
|
FINISHED |
| Object | manned lighthouse |
—
|
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: manned lighthouse | Statement: [Plymouth Breakwater Lighthouse, originalOperation, manned lighthouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalOperation Context triple: [Plymouth Breakwater Lighthouse, originalOperation, manned lighthouse]
-
A.
primaryOperation
chosen
Indicates the main or most important operation performed or used by an entity in a given context.
-
B.
inOperationFrom
Indicates that an entity (such as a facility, service, or system) is actively functioning or available starting from a specified point in time.
-
C.
associatedOperation
Indicates that one entity is linked to or involved with a particular operation, process, or activity.
-
D.
operationOf
Indicates that one entity is the function, activity, or process carried out by another entity (such as a system, device, or organization).
-
E.
intendedOperationFrom
Indicates that one entity is the source or origin of a planned or intended operation involving another 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d5402ad881908add559249278895 |
completed | April 20, 2026, 7:26 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 11:59 a.m.