Triple
T3474815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mendocino Fracture Zone |
E73345
|
entity |
| Predicate | trendDirection |
P39078
|
FINISHED |
| Object | east–west |
—
|
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: east–west | Statement: [Mendocino Fracture Zone, trendDirection, east–west]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trendDirection Context triple: [Mendocino Fracture Zone, trendDirection, east–west]
-
A.
hasTrend
Indicates that something exhibits or is associated with a particular pattern of change or direction over time.
-
B.
trends
chosen
Indicates that one entity exhibits a general direction of change or development over time in relation to another reference or context.
-
C.
directionalExtreme
Indicates that one entity lies at or near the furthest extent or boundary in a specified direction relative to another entity.
-
D.
trendDownGroup
Indicates a relationship where a group collectively exhibits a downward trend in some measured value or performance over time.
-
E.
containsDirectionOf
Indicates that one entity includes or encompasses the directional orientation or path associated with another 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_69ad85b2fed48190948c8765e453d270 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbb580d4c819080bcc0bccd1e18e2 |
completed | March 8, 2026, 6:09 p.m. |
| PD | Predicate disambiguation | batch_69adae07802c8190919c49b0e65b2797 |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:17 p.m.