Triple
T25118662
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ned’s Point Lighthouse |
E629205
|
entity |
| Predicate | yearReactivated |
P34676
|
FINISHED |
| Object | 1943 |
—
|
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: 1943 | Statement: [Ned’s Point Lighthouse, yearReactivated, 1943]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearReactivated Context triple: [Ned’s Point Lighthouse, yearReactivated, 1943]
-
A.
reactivatedDuring
Indicates that an entity becomes active again within the time span or context defined by another event or condition.
-
B.
reactivatedFrom
Indicates that an entity has been brought back into an active state from a previously inactive, archived, or decommissioned state, often referencing the source state or version it was reactivated from.
-
C.
reactivationOutcome
Indicates the result or consequence that follows from a reactivation event or process.
-
D.
activeInYears
chosen
Indicates that an entity was active or operational during the specified years or year range.
-
E.
reaffirmationYear
Indicates the year in which a previously established agreement, decision, or commitment is formally confirmed or renewed.
- 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_69e2ff3169d08190973b6061d5009abd |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f465c9bad88190b1488ada06e9b51b |
completed | May 1, 2026, 8:35 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:27 a.m.