Triple
T891782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heinrich Hertz |
E19253
|
entity |
| Predicate | verified |
P653
|
FINISHED |
| Object | Maxwell's equations experimentally |
—
|
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: Maxwell's equations experimentally | Statement: [Heinrich Hertz, verified, Maxwell's equations experimentally]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: verified Context triple: [Heinrich Hertz, verified, Maxwell's equations experimentally]
-
A.
confirmedBy
chosen
Indicates that one entity validates, approves, or verifies the truth, accuracy, or occurrence of another entity or event.
-
B.
confirmedFor
Indicates that an entity has been officially approved, scheduled, or validated to participate in, receive, or be associated with another specified entity or event.
-
C.
reviewedBy
Indicates that an item, work, or action has been examined and evaluated by a specific agent or reviewer.
-
D.
committed
Indicates that an agent has carried out or been responsible for a specific act, event, or wrongdoing.
-
E.
signedFor
Indicates that one entity formally accepted or acknowledged receipt of something on behalf of another, typically by providing a signature.
- 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_69a4939d37188190848be3d426ebc9ae |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4ad019e448190ab991e85dc6d7708 |
completed | March 1, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69a4aa9372e88190b5a9db4afdc045c6 |
completed | March 1, 2026, 9:07 p.m. |
Created at: March 1, 2026, 7:39 p.m.