Triple
T24138626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wabash, Indiana |
E598160
|
entity |
| Predicate | electricalLightingPioneer |
P122909
|
FINISHED |
| Object | Charles F. Brush |
—
|
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: Charles F. Brush | Statement: [Wabash, Indiana, electricalLightingPioneer, Charles F. Brush]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electricalLightingPioneer Context triple: [Wabash, Indiana, electricalLightingPioneer, Charles F. Brush]
-
A.
electricSystemPioneer
chosen
Indicates that the subject was an early innovator or leading contributor in the development or implementation of electric systems.
-
B.
firstLightingYear
Indicates the year in which something (such as a light source or lighting installation) was first put into operation or illuminated.
-
C.
pioneerOf
Indicates that an entity was among the first to develop, introduce, or significantly advance another entity, concept, or practice.
-
D.
hasRelationshipToElectricLight
Indicates that one entity has a specified type of connection, association, or relevance to an electric light.
-
E.
featuresLightingBy
Indicates that something includes or showcases lighting created, provided, or designed by a specified 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_69e288c92e448190ac57034fa0c863ce |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1df7e3c20819099ff289789829d7e |
completed | April 29, 2026, 10:37 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:27 p.m.