Triple
T3284048
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crater Glacier |
E68938
|
entity |
| Predicate | shelteredBy |
P957
|
FINISHED |
| Object | crater walls of Mount St. Helens |
—
|
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: crater walls of Mount St. Helens | Statement: [Crater Glacier, shelteredBy, crater walls of Mount St. Helens]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shelteredBy Context triple: [Crater Glacier, shelteredBy, crater walls of Mount St. Helens]
-
A.
hadSanctuaryOf
Indicates that an entity possessed or hosted a sanctuary dedicated to another entity.
-
B.
hasNearbySanctuary
Indicates that one entity has a sanctuary or place of refuge located close to it in space or distance.
-
C.
hasShelters
Indicates that one entity provides, contains, or is associated with one or more shelters for another entity or purpose.
-
D.
protectedBy
chosen
Indicates that one entity provides protection, defense, or safeguarding for another entity.
-
E.
protectedGround
Indicates that one entity has taken action to safeguard or defend another entity or area from harm, damage, or unauthorized interference.
- 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_69ad859c463481909ca4be267336c290 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb03621608190a2b7a6b38d6559da |
completed | March 8, 2026, 5:21 p.m. |
| PD | Predicate disambiguation | batch_69ada421fadc8190b7c7d3c8afd20061 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:10 p.m.