Triple
T13747276
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Teton fault |
E330244
|
entity |
| Predicate | hasMaximumSingleEventDisplacement |
P84064
|
FINISHED |
| Object | several meters |
—
|
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: several meters | Statement: [Teton fault, hasMaximumSingleEventDisplacement, several meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMaximumSingleEventDisplacement Context triple: [Teton fault, hasMaximumSingleEventDisplacement, several meters]
-
A.
hasMaxDisplacement
chosen
Indicates the maximum distance or extent to which something can move or be displaced from its original position.
-
B.
maximumHorizontalDisplacement
Indicates the greatest distance an entity can or does move horizontally from a reference point or along a horizontal axis.
-
C.
maximumDischarge
Indicates the greatest allowable or observed rate at which something can be discharged or released from a source.
-
D.
hasDisplacement
Indicates a relationship where an entity experiences or is assigned a change in position or location from an initial point to a final point.
-
E.
isMaximumWhen
Indicates that a quantity or function reaches its greatest possible value under specified conditions or at a particular point.
- 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_69d81c573f288190aa2403d484fa3d49 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de02132a108190aca728b95e83af01 |
completed | April 14, 2026, 9 a.m. |
| PD | Predicate disambiguation | batch_69dbbe950b148190ba0df8a749269ec6 |
completed | April 12, 2026, 3:47 p.m. |
Created at: April 9, 2026, 10:08 p.m.