Triple
T1390213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Round Island Lighthouse |
E29936
|
entity |
| Predicate | reactivated |
P12197
|
FINISHED |
| Object | 1996 |
—
|
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: 1996 | Statement: [Round Island Lighthouse, reactivated, 1996]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reactivated Context triple: [Round Island Lighthouse, reactivated, 1996]
-
A.
reintroduced
Indicates that an entity that was previously removed, extinct, or absent has been brought back or restored to a place, context, or state.
-
B.
recommissioned
chosen
Indicates that something previously deactivated, retired, or out of service has been restored and formally returned to active use or operation.
-
C.
restored
Indicates that an entity has returned another entity to a previous or improved state, condition, or position after damage, loss, or alteration.
-
D.
recreated
Indicates that an entity has been created again or restored, typically after being removed, destroyed, or significantly altered.
-
E.
revivedBy
Indicates that an entity has been brought back to life, consciousness, or active state through the action or intervention of 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_69a498dc92f8819094a1108f8ac90f43 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c35e023c8190b45688796d90534b |
completed | March 1, 2026, 10:53 p.m. |
| PD | Predicate disambiguation | batch_69a4beffcf808190ab4cd0271257ce63 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:59 p.m.