Triple
T28085406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Historic Fort Nisqually |
E709807
|
entity |
| Predicate | reconstructsPeriod |
P16794
|
FINISHED |
| Object | 1830s |
—
|
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: 1830s | Statement: [Historic Fort Nisqually, reconstructsPeriod, 1830s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reconstructsPeriod Context triple: [Historic Fort Nisqually, reconstructsPeriod, 1830s]
-
A.
reconstructedDuring
Indicates that an entity was rebuilt, restored, or significantly repaired within a specified time period or event.
-
B.
reconstructionPeriod
chosen
Indicates a time span during which something that was damaged, destroyed, or altered is being rebuilt, restored, or substantially repaired.
-
C.
reconstructs
Indicates performing an action to rebuild, restore, or reassemble something from its parts, damage, or prior state.
-
D.
reconstructedFor
Indicates that something has been rebuilt, restored, or re-created for the benefit, use, or purpose of another entity.
-
E.
reconstructedEvery
Indicates that one entity has rebuilt or restored every instance of another entity completely.
- 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_69ef9b7037f0819095bb90eaccbcaf32 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a931748190a637e631a52bbfaa |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 27, 2026, 8:54 p.m.