Triple
T36923685
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nootka Trading Company |
E913275
|
entity |
| Predicate | isReclaimedBy |
P93744
|
FINISHED |
| Object | James Keziah Delaney |
—
|
NE NERFINISHED |
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: James Keziah Delaney | Statement: [Nootka Trading Company, isReclaimedBy, James Keziah Delaney]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isReclaimedBy Context triple: [Nootka Trading Company, isReclaimedBy, James Keziah Delaney]
-
A.
isReclaimedFrom
chosen
Indicates that something has been recovered, restored, or taken back from a previous state, owner, or condition.
-
B.
isReclaimed
Indicates that something previously used, degraded, or discarded has been restored, recovered, or converted back into a usable or improved state.
-
C.
partlyReclaimedAs
Indicates that one entity has been partially converted, restored, or taken back into the state, use, or condition represented by the other entity.
-
D.
isReclamationExampleOf
Indicates that one entity serves as an instance or illustration of reclamation in relation to another entity.
-
E.
hasReclamationType
Indicates the specific method or category of reclamation associated with an entity, such as how land, materials, or resources are recovered or restored.
- 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.