Triple
T80970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles Lyell |
E1625
|
entity |
| Predicate | inferredFrom |
P1661
|
FINISHED |
| Object | 19th-century Scottish geologist description |
—
|
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: 19th-century Scottish geologist description | Statement: [Charles Lyell, inferredFrom, 19th-century Scottish geologist description]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: inferredFrom Context triple: [Charles Lyell, inferredFrom, 19th-century Scottish geologist description]
-
A.
derivedFrom
Indicates that one entity originates, is obtained, or is developed from another source entity.
-
B.
formedBy
Indicates that something comes into existence or is created as a result of a specific agent, process, or combination of components.
-
C.
implies
chosen
Indicates that the truth of one statement guarantees or leads logically to the truth of another statement.
-
D.
isBackboneOf
Indicates that one entity forms the main supporting structure or central framework upon which another entity fundamentally depends.
-
E.
developedFrom
Indicates that one entity originates, evolves, or is derived from another as its source or precursor.
- 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_69a24c60d19c8190a1b6c105ca59ef5b |
completed | Feb. 28, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69a25053ca208190a371b0d38000c2b9 |
completed | Feb. 28, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69a24eb2998c819082681da74601d446 |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:06 a.m.