Triple
T16922728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Thomson |
E410479
|
entity |
| Predicate | hasInvented |
P632
|
FINISHED |
| Object | pneumatic road vehicle tyre |
—
|
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: pneumatic road vehicle tyre | Statement: [Robert Thomson, hasInvented, pneumatic road vehicle tyre]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInvented Context triple: [Robert Thomson, hasInvented, pneumatic road vehicle tyre]
-
A.
hasInventionProperty
Indicates that an entity possesses a specific characteristic, attribute, or quality related to an invention.
-
B.
wasInventedBy
chosen
Indicates that something (typically an object, concept, or process) was created or brought into existence by a particular inventor or originator.
-
C.
notableInventor
Indicates that the subject is a well-known or historically significant inventor of the object.
-
D.
hasKeyInvention
Indicates that an entity possesses or is associated with a primary or crucial invention.
-
E.
invention
Indicates that one entity is the creator or originator of another entity, typically a device, method, or idea.
- 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_69d886c7b1e481908c3766dfa8c13458 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3cdf06e8c81908028efef2faa6c6b |
completed | April 18, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69e32b982f548190b08414d55810de19 |
completed | April 18, 2026, 6:58 a.m. |
Created at: April 10, 2026, 5:30 a.m.