Triple
T22565151
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | D66 |
E557927
|
entity |
| Predicate | hasGeologicalOriginOfStones |
P66958
|
FINISHED |
| Object | Pleistocene glaciation |
—
|
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: Pleistocene glaciation | Statement: [D66, hasGeologicalOriginOfStones, Pleistocene glaciation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasGeologicalOriginOfStones Context triple: [D66, hasGeologicalOriginOfStones, Pleistocene glaciation]
-
A.
geologicalOriginOfStones
chosen
Indicates the geological source or formation process from which particular stones originate.
-
B.
hasGeologicalNature
Indicates that something possesses a specific geological character, composition, or formation type.
-
C.
hasMaterialOfStones
Indicates that something is composed of or contains a particular type or set of stones as its material.
-
D.
hasGeologicalSignificance
Indicates that something possesses notable importance or relevance within a geological context, such as Earth’s structure, history, or processes.
-
E.
hasStateRockFormation
Indicates a relationship where a state is associated with or designated as having a particular rock formation.
- 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_69e11e5ae4ac8190b1f503457603d969 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15fa9ebc8819098d74fb41e14bd7e |
completed | April 29, 2026, 1:32 a.m. |
| PD | Predicate disambiguation | batch_69ee626e6bb08190ada4dd8b48cc0c43 |
completed | April 26, 2026, 7:07 p.m. |
Created at: April 16, 2026, 8:52 p.m.