Triple
T14636297
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Water |
E343615
|
entity |
| Predicate | roleInGeology |
P14294
|
FINISHED |
| Object | agent of erosion |
—
|
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: agent of erosion | Statement: [Water, roleInGeology, agent of erosion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInGeology Context triple: [Water, roleInGeology, agent of erosion]
-
A.
geologicalRole
chosen
Indicates the functional or classificatory role an entity plays within geological processes, structures, or contexts.
-
B.
geologyRelatedTo
Indicates a relationship where one geological entity, feature, or concept is connected, associated, or relevant to another within the domain of geology.
-
C.
geologicalStudyField
Indicates that a particular field or area is the subject or location of a geological study or investigation.
-
D.
geologyStudiedBy
Indicates that a geological feature, subject, or area is the object of study or research conducted by a specified person or organization.
-
E.
geologyIncludes
Indicates that one geological entity contains, encompasses, or has as a component another geological 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_69d822dffc3c8190aa173b90761bffda |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4ab9578819085b4cf7244d30d87 |
completed | April 14, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69de657359c88190b082e3e9f86fc1d7 |
completed | April 14, 2026, 4:04 p.m. |
Created at: April 10, 2026, 1:26 a.m.