Triple
T30971572
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tulelake, California |
E789111
|
entity |
| Predicate | hasNearbyGeologicFeature |
P52075
|
FINISHED |
| Object | volcanic terrain of the Modoc Plateau |
—
|
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: volcanic terrain of the Modoc Plateau | Statement: [Tulelake, California, hasNearbyGeologicFeature, volcanic terrain of the Modoc Plateau]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyGeologicFeature Context triple: [Tulelake, California, hasNearbyGeologicFeature, volcanic terrain of the Modoc Plateau]
-
A.
nearGeologicalSite
chosen
Indicates that one entity is located in close physical proximity to a geological site or feature.
-
B.
hasNearbyRockFormation
Indicates that one entity is located close to or adjacent to a rock formation.
-
C.
hasNearbyMarineFeature
Indicates that one entity is located close to a marine geographic feature associated with the other entity.
-
D.
shareGeologicalFeature
Indicates that two or more entities have a geological feature in common, such as sharing the same type, structure, or formation.
-
E.
hasNearbyPromontory
Indicates that one geographic feature or location is situated close to a promontory or headland.
- 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_69f224c4831c8190be53924ec25a150a |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fec8aef1d8819094c7fd7074038e6b |
completed | May 9, 2026, 5:39 a.m. |
| PD | Predicate disambiguation | batch_69fec639876481908efd84a3631a4271 |
completed | May 9, 2026, 5:29 a.m. |
Created at: April 29, 2026, 8:55 p.m.